© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56728
    Prev
    Next
    INDEX
    Explanations

    mathematical section titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ²,
    -0.90
     iveco
    -0.83
    めました
    -0.81
    AYA
    -0.79
     twij
    -0.78
    °;
    -0.77
     biel
    -0.77
     galo
    -0.76
     €,
    -0.76
     Lb
    -0.75
    POSITIVE LOGITS
     (
    1.38
     Let
    1.18
     let
    1.15
     [
    1.13
    Retention
    1.01
    商品は
    0.98
     ([
    0.94
    bisoft
    0.91
    astify
    0.90
    UnknownFields
    0.89
    Activations Density 0.004%

    No Known Activations