© 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. 22-GEMMASCOPE-RES-131K
    7. 127946
    Prev
    Next
    INDEX
    Explanations

    export, output, or version

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     women
    -1.21
    指輪
    -1.03
     rossz
    -1.01
     relógio
    -0.98
     deportivas
    -0.97
     people
    -0.96
     nuevos
    -0.96
     incoming
    -0.93
    ようになりました
    -0.93
     входа
    -0.93
    POSITIVE LOGITS
     output
    1.48
     outputs
    1.27
     النها
    1.22
     export
    1.16
    output
    1.13
     بعد
    1.12
    Efter
    1.09
    final
    1.05
     final
    1.03
    После
    1.01
    Activations Density 0.129%

    No Known Activations