© 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. 113882
    Prev
    Next
    INDEX
    Explanations

    vim configuration endings

    np_acts-logits-general · gemini-2.5-flash-lite

    closing HTML/XML tags and code syntax elements like brackets, underscores, and special characters in technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    鍇
    -1.30
    DQ
    -1.27
     cedera
    -1.24
    THERE
    -1.23
    viewpager
    -1.20
     ço
    -1.20
     Obtén
    -1.18
    athic
    -1.18
    鮋
    -1.18
     yaklaş
    -1.17
    POSITIVE LOGITS
     their
    1.36
     which
    1.25
     his
    1.24
     those
    1.18
     that
    1.18
     its
    1.15
     when
    1.09
     bureaux
    1.06
     Both
    1.05
    Зе
    1.04
    Activations Density 0.187%

    No Known Activations