© 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. 98889
    Prev
    Next
    INDEX
    Explanations

    list items

    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
    ਲ਼
    -2.17
     verle
    -2.02
     imponer
    -1.95
    瓛
    -1.91
    Kontra
    -1.89
     Istri
    -1.87
     saati
    -1.86
     ation
    -1.80
     StringVar
    -1.80
     Asie
    -1.79
    POSITIVE LOGITS
    {
    2.17
     and
    2.17
     to
    2.13
     It
    2.08
    <
    1.87
     
    1.79
    >
    1.79
     &
    1.79
     is
    1.76
    G
    1.72
    Activations Density 0.007%

    No Known Activations