© 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. 123996
    Prev
    Next
    INDEX
    Explanations

    create content, returned without

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

    crucial for

    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
    owanych
    0.57
     செய்த
    0.50
    <unused64>
    0.48
     problemler
    0.46
    建筑
    0.45
    وجوان
    0.45
     पड़े
    0.45
    낯
    0.45
    他们的
    0.45
    മ്പോ
    0.44
    POSITIVE LOGITS
    O
    0.59
     Ok
    0.52
    н
    0.52
     ok
    0.50
    ن
    0.50
     Oy
    0.48
     to
    0.48
     (
    0.47
    mond
    0.47
     Generals
    0.47
    Activations Density 0.000%

    No Known Activations