© 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. 106151
    Prev
    Next
    INDEX
    Explanations

    numbers in brackets or punctuation

    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
     everything
    -1.02
     those
    -1.01
     its
    -0.97
    mohon
    -0.94
     where
    -0.92
     theatrical
    -0.92
    //};
    -0.92
     kwiet
    -0.92
     worst
    -0.91
     perhaps
    -0.91
    POSITIVE LOGITS
     [
    1.11
     enanti
    0.96
     officiel
    0.95
    k
    0.90
    u
    0.88
     Usual
    0.88
    водить
    0.85
     Udaipur
    0.84
     upholstered
    0.84
     beeintr
    0.83
    Activations Density 0.003%

    No Known Activations