© 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. 130152
    Prev
    Next
    INDEX
    Explanations

    lists of items

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

    safer path

    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
    Negative Logits
     cheesecake
    0.50
     mum
    0.48
     printed
    0.47
     Keeper
    0.46
     comentario
    0.46
     Ved
    0.46
     همچ
    0.45
     کمپنی
    0.45
     글
    0.45
     nomenclature
    0.45
    POSITIVE LOGITS
     ≠
    0.58
    ≠
    0.52
    istere
    0.48
    并通过
    0.47
     አይ
    0.46
    italizationType
    0.46
    是因为
    0.45
    Obama
    0.44
    受伤
    0.44
    延长
    0.43
    Activations Density 0.003%

    No Known Activations