© 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. 67857
    Prev
    Next
    INDEX
    Explanations

    attractions IS Michel attractions

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

    access, permissions, elasticity, build

    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
    Not in Any Lists

    No Comments

    Negative Logits
     preoccupation
    0.46
    technik
    0.46
    돗
    0.45
    جري
    0.43
     Comercio
    0.43
    berto
    0.42
    鸡蛋
    0.42
     字
    0.42
    methanol
    0.41
     油
    0.41
    POSITIVE LOGITS
    ৫
    0.54
    केशन
    0.50
    าย
    0.49
    ləşdirilib
    0.49
    า
    0.48
    ա
    0.47
     perfection
    0.47
    ់
    0.47
    া
    0.47
     rebellion
    0.47
    Activations Density 0.000%

    No Known Activations