© 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. 77857
    Prev
    Next
    INDEX
    Explanations

    permit professionals get it done

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

    program, Timer, trace, need

    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
     WARRANT
    0.42
    ge
    0.41
    🌶
    0.41
    platte
    0.41
    મિંગ
    0.40
    sign
    0.39
     warrants
    0.39
    मिया
    0.39
    hend
    0.39
    symbols
    0.39
    POSITIVE LOGITS
     Аб
    0.45
     sağ
    0.43
     methodological
    0.43
     Alderman
    0.43
    自我
    0.42
     ادارے
    0.42
     Ảnh
    0.42
    ١
    0.42
     Apesar
    0.41
     Comercial
    0.41
    Activations Density 0.000%

    No Known Activations