© 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. 111282
    Prev
    Next
    INDEX
    Explanations

    directives, forecasts, changes, descriptions

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

    enumeration methods

    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
     орби
    0.55
     വേണ്ടി
    0.54
     ລັບ
    0.51
     باتوں
    0.50
     کارگرد
    0.49
     नवीनतम
    0.49
     ஓடுப
    0.49
    🏤
    0.49
     قوانین
    0.49
    銑
    0.49
    POSITIVE LOGITS
     that
    0.58
    K
    0.54
    G
    0.54
    L
    0.51
    B
    0.51
    A
    0.50
    ,
    0.49
     over
    0.49
    WV
    0.48
    BD
    0.47
    Activations Density 0.000%

    No Known Activations