© 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. 14882
    Prev
    Next
    INDEX
    Explanations

    information except

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

    after punctuation

    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
    지와
    0.46
     விரும்ப
    0.43
     Ideally
    0.42
    直播
    0.41
    未能
    0.41
    地
    0.41
    없
    0.41
     முய
    0.40
    本科
    0.40
    정과
    0.40
    POSITIVE LOGITS
     anymore
    0.56
     paycheck
    0.43
     fratello
    0.43
     ș
    0.42
     který
    0.42
     paparazzi
    0.42
     MasterCard
    0.42
     diva
    0.42
     ദുൽ
    0.42
    redo
    0.41
    Activations Density 0.001%

    No Known Activations