How Neighborhood Note Signal Extractor works
Press Load model once: your browser downloads Gemma 4 E2B instruction-tuned (web build) (2.0 GB) from this site and keeps it in its cache. Then add your text and press Extract locally. The model runs on this device using your graphics card, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.
Gemma 4 E2B instruction-tuned (web build) is a small open language model from Google. The tool sends it the instruction below plus your text, asks for a JSON answer with fixed fields, and shows each field as a card. It runs at temperature 0, so the same input gives the same answer on the same device, though different graphics cards can word it slightly differently.
Inputs longer than 6,000 characters are cut to that length before they reach the model, and the result says so. The model only sees what you paste: it does not look anything up.
The instruction the model gets
You turn notes about a neighbourhood into signals a home buyer or renter can act on: positives (transit, walkability, parks, shops, schools as named), concerns (noise, traffic, parking, flooding, construction) and things to verify in person or with official sources. Describe places, services and conditions only. Never describe or guess who lives in the area, its demographics, religion or ethnicity, and never call an area safe or unsafe; point to official crime maps or local sources instead. Do not invent places that are not in the notes.
What it returns
- Positives: Good signals from the notes, in their words.
- Concerns: Drawbacks from the notes, in their words, with times or days as written.
- Check before deciding: Two or three things to confirm on a visit or from an official source.