© 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. 47021
    Prev
    Next
    INDEX
    Explanations

    historical societies and organizations

    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
    initro
    -0.76
    LastModified
    -0.75
    (/[
    -0.73
    ถึง
    -0.72
     producer
    -0.70
     ILO
    -0.69
    Equipe
    -0.68
     navigating
    -0.67
     מן
    -0.66
    strm
    -0.66
    POSITIVE LOGITS
     Daughters
    1.97
     DAR
    1.56
    DAR
    1.43
     NSD
    1.10
    aughters
    1.10
     Sons
    0.96
     daughters
    0.95
    SAR
    0.93
     Daughter
    0.92
     SAR
    0.90
    Activations Density 0.014%

    No Known Activations