© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 158281
    Prev
    Next
    INDEX
    Explanations

    specific housing programs

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

    follow specific rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viagens
    0.51
     tiendas
    0.49
     perched
    0.48
    疼
    0.48
     sillas
    0.47
     dieting
    0.46
     protruding
    0.46
     bruised
    0.46
     douceur
    0.46
     troupes
    0.45
    POSITIVE LOGITS
     ਦੇ
    0.50
     Сле
    0.48
     ㅅ
    0.48
     С
    0.47
     Р
    0.47
     확장
    0.46
     ස
    0.46
     कार्बन
    0.46
     Blok
    0.46
     Нор
    0.46
    Activations Density 0.000%

    No Known Activations