© 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. 10-GEMMASCOPE-RES-131K
    7. 72202
    Prev
    Next
    INDEX
    Explanations

    link parsing

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     if
    -2.72
     it
    -2.17
    های
    -1.98
     slated
    -1.86
    🌸
    -1.85
     atau
    -1.83
     there
    -1.82
    🌟
    -1.79
    两年
    -1.79
    ynthetic
    -1.78
    POSITIVE LOGITS
    <bos>
    2.56
     are
    2.23
     которые
    2.20
    pecabe
    2.13
     которыми
    2.08
     themselves
    2.06
     meisten
    2.06
    衚
    2.05
    不但
    2.05
    providedIn
    2.05
    Activations Density 0.015%

    No Known Activations