© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33533
    Prev
    Next
    INDEX
    Explanations

    real estate listings and prices

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on the structured numeric and keyword patterns typical of real‐estate listings—MLS identifiers, prices, and counts of bedrooms and bathrooms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     évé
    -1.27
     éd
    -1.22
    :+:
    -1.15
     sapat
    -1.09
    gré
    -1.09
     arit
    -1.08
     tarta
    -1.06
    fangs
    -1.06
     Apk
    -1.05
    tellte
    -1.05
    POSITIVE LOGITS
     szint
    1.30
     również
    1.27
     также
    1.21
    Amical
    1.18
     similar
    1.17
     $
    1.13
     convertido
    1.13
     cubierto
    1.09
     européennes
    1.08
    ありますが
    1.06
    Activations Density 0.002%

    No Known Activations