© 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. 153437
    Prev
    Next
    INDEX
    Explanations

    is that

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

    adrenaline, authority, effort

    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
    ing
    0.49
    ;
    0.47
     неравен
    0.46
    erna
    0.46
     লিখতে
    0.46
     прой
    0.46
     Cub
    0.45
     grueling
    0.44
     আনুষ্ঠানিক
    0.43
    🐺
    0.43
    POSITIVE LOGITS
    జ్‌
    0.49
    ક્સ
    0.49
     เศษ
    0.47
    జ్
    0.47
    స్కీ
    0.47
    䛛
    0.46
     Dương
    0.46
    딪
    0.45
    getRow
    0.44
    iteľ
    0.44
    Activations Density 0.001%

    No Known Activations