© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 146699
    Prev
    Next
    INDEX
    Explanations

    accounting for context

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

    Global Area, Media Kits, intercept calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     इंट्रोडक्शन
    0.48
    磷
    0.47
     फ्रेम
    0.47
    襁
    0.47
    フレーム
    0.46
     अवलंब
    0.46
     предмет
    0.45
    夗
    0.45
    펄
    0.45
     Сою
    0.44
    POSITIVE LOGITS
    AR
    0.60
    ARTER
    0.54
     on
    0.52
     who
    0.51
     worn
    0.49
    IA
    0.49
     billboard
    0.49
    AT
    0.49
     with
    0.48
     from
    0.48
    Activations Density 0.000%

    No Known Activations