© 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. 79384
    Prev
    Next
    INDEX
    Explanations

    top that

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

    App actions and pasta dishes

    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
    Individuals
    0.48
    诺
    0.47
    倾
    0.44
    潮
    0.42
     Goldstein
    0.42
    ad
    0.41
    ब
    0.40
    駄
    0.40
    Enders
    0.40
    ب
    0.38
    POSITIVE LOGITS
    reqParam
    0.53
     ܗ
    0.52
     req
    0.51
    REQUIRE
    0.51
     neke
    0.50
     salesman
    0.50
     পারছি
    0.48
     harmonica
    0.48
    {}'.
    0.48
     middlewares
    0.47
    Activations Density 0.000%

    No Known Activations