© 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. 166701
    Prev
    Next
    INDEX
    Explanations

    life success

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

    modelcell type identification

    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
    氧化
    0.49
     գ
    0.46
    齐全
    0.46
     nhựa
    0.45
     thích
    0.45
     конденса
    0.44
     কাতর
    0.44
     điều
    0.44
     добре
    0.44
     getMain
    0.43
    POSITIVE LOGITS
    ObjectType
    0.57
    oram
    0.54
    E
    0.52
    U
    0.49
    ara
    0.49
    Ile
    0.48
    II
    0.47
    yta
    0.46
    angan
    0.46
     promulgate
    0.45
    Activations Density 0.001%

    No Known Activations