© 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. 68619
    Prev
    Next
    INDEX
    Explanations

    link and code delimiters

    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
     favoriser
    -1.80
    臜
    -1.76
     sellado
    -1.75
    ㌧
    -1.70
     capaces
    -1.70
     activado
    -1.66
     ろ
    -1.66
     quintessential
    -1.63
     eficientes
    -1.63
    넵
    -1.63
    POSITIVE LOGITS
     their
    2.69
     at
    2.31
     or
    1.99
     the
    1.95
     “
    1.87
     this
    1.85
     some
    1.76
     (
    1.75
     /
    1.70
     Their
    1.70
    Activations Density 0.003%

    No Known Activations