© 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. 57989
    Prev
    Next
    INDEX
    Explanations

    SCIENCE, water, crystal, sport, application

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

    technical or academic terminology across various scientific and specialized fields.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
     with
    -2.33
     after
    -2.06
     not
    -1.93
     several
    -1.92
     some
    -1.84
     three
    -1.70
     Several
    -1.70
     as
    -1.70
     because
    -1.69
     seven
    -1.67
    POSITIVE LOGITS
     unveils
    1.80
     créer
    1.76
     manquer
    1.73
     revamped
    1.71
     fiasco
    1.66
     poign
    1.64
     THOSE
    1.63
    ,;
    1.58
     huiles
    1.57
     overarching
    1.55
    Activations Density 4.860%

    No Known Activations