© 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. 22570
    Prev
    Next
    INDEX
    Explanations

    opposition, rivals, enemies

    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
    Not in Any Lists

    No Comments

    Negative Logits
    诋
    -1.44
     ū
    -1.41
    licado
    -1.34
    getExtras
    -1.30
     发表于
    -1.23
     Kalman
    -1.20
    دواج
    -1.20
    larımız
    -1.18
    eches
    -1.17
     мон
    -1.17
    POSITIVE LOGITS
     with
    1.62
     unless
    1.52
     either
    1.51
     until
    1.41
     it
    1.38
     deemed
    1.34
     up
    1.33
     higher
    1.30
     you
    1.29
     prioridades
    1.28
    Activations Density 0.028%

    No Known Activations