© 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. 78182
    Prev
    Next
    INDEX
    Explanations

    showroom or uncontrolled

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

    how to define it

    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
    летов
    0.49
    ที่ไม่
    0.47
    </h2>
    0.46
    <0x0D>
    0.46
    -
    0.46
    от
    0.45
    5
    0.45
     Jokowi
    0.44
     ख्
    0.43
    Dios
    0.43
    POSITIVE LOGITS
    爱好者
    0.45
    gramModel
    0.44
    ግሎ
    0.44
    män
    0.44
     পিঁপড়ার
    0.44
    𒃶
    0.43
     সংগ্রহ
    0.43
     餐
    0.43
     ವ್ಯವ
    0.42
     బోర్
    0.42
    Activations Density 0.000%

    No Known Activations