© 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. 248876
    Prev
    Next
    INDEX
    Explanations

    Theater -Origin CDfail .4 .keep withinknow this. Youmeans aMa ,to try

    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
     artı
    0.48
    त्रे
    0.46
    রাজনৈতিক
    0.46
    RIBUTE
    0.46
    体
    0.45
    畕
    0.45
     gifts
    0.44
    '
    0.44
    结合
    0.43
     atypical
    0.43
    POSITIVE LOGITS
     あ
    0.57
    oi
    0.50
     ラン
    0.50
     顔
    0.49
     जानिए
    0.49
     大家
    0.49
     ハ
    0.49
     シェ
    0.49
     裏
    0.49
     現在
    0.48
    Activations Density 0.000%

    No Known Activations