© 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. 239874
    Prev
    Next
    INDEX
    Explanations

    related to government and organization

    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
    ۸
    0.49
    ۵
    0.48
    льт
    0.47
    <0xAE>
    0.45
    熊
    0.44
     लाया
    0.43
    公路
    0.43
    <0xA8>
    0.43
     ដែល
    0.42
    ۷
    0.42
    POSITIVE LOGITS
     피부
    0.52
    etheless
    0.51
    皮膚
    0.49
     ভর
    0.48
    dures
    0.48
    in
    0.47
    carn
    0.47
    visit
    0.47
    with
    0.46
    处于
    0.46
    Activations Density 0.000%

    No Known Activations