© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 213230
    Prev
    Next
    INDEX
    Explanations

    doing, creating, or plotting

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

    functions make code reusable

    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
    Negative Logits
    诟
    0.49
     чемпионате
    0.46
    াড়ার
    0.43
    ोध
    0.42
     Разби
    0.42
    蝴
    0.42
    landmarks
    0.42
     Corvette
    0.40
     Adhesive
    0.40
    boundingBox
    0.39
    POSITIVE LOGITS
    CreationFailed
    0.48
     it
    0.45
     prolog
    0.45
     olyan
    0.45
     intolerable
    0.45
    %
    0.45
     prettier
    0.45
    magenta
    0.44
    PLE
    0.44
    ਲ
    0.44
    Activations Density 0.000%

    No Known Activations