© 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. 45514
    Prev
    Next
    INDEX
    Explanations

    (abbreviations) followed by IL

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

    abbreviations and parenthetical notations in scientific or medical texts.

    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
     ihre
    -2.09
    ”
    -1.99
    $,
    -1.89
    In
    -1.88
    <em>
    -1.80
    €™
    -1.80
    Then
    -1.78
    他的
    -1.74
    *,
    -1.74
     seine
    -1.73
    POSITIVE LOGITS
     continúas
    1.94
    ቷ
    1.93
     propuesto
    1.77
    ﻒ
    1.77
    蒟
    1.73
     desbloquear
    1.71
     trabajó
    1.70
     firmado
    1.69
     Ně
    1.67
    ながらも
    1.66
    Activations Density 0.370%

    No Known Activations