© 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. 34400
    Prev
    Next
    INDEX
    Explanations

    RWKV, Activity, Integrated

    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
    r
    0.63
    d
    0.58
    ת
    0.57
    t
    0.56
    l
    0.54
    m
    0.51
    ર
    0.48
    ر
    0.47
    ت
    0.47
    e
    0.47
    POSITIVE LOGITS
     Ensures
    0.50
     rougeâtres
    0.48
     arrondies
    0.45
     таблицы
    0.44
    erequisites
    0.44
    ेंद्रीय
    0.44
    エラー
    0.44
     nécessaires
    0.43
     ইহাদের
    0.43
     xWidth
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.