© 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. 62535
    Prev
    Next
    INDEX
    Explanations

    pdf references in code

    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
     plafon
    -0.95
    歺
    -0.84
    ӡ
    -0.82
     huwa
    -0.81
    <0xD7>
    -0.81
     mitig
    -0.76
     Walla
    -0.76
    IPPING
    -0.76
     verte
    -0.75
    offering
    -0.75
    POSITIVE LOGITS
     <
    1.07
    ↵↵↵
    0.98
    ↵↵↵↵
    0.91
    icycle
    0.88
     inspirasi
    0.82
    ↵
    0.81
     khusus
    0.79
     /(
    0.78
     using
    0.77
    話し
    0.76
    Activations Density 0.002%

    No Known Activations