© 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. 81478
    Prev
    Next
    INDEX
    Explanations

    responsible for organizing

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

    referring to or defining properties

    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
    de
    0.73
    le
    0.60
    2
    0.59
    r
    0.58
    U
    0.58
    C
    0.57
    E
    0.57
    1
    0.57
    X
    0.57
    R
    0.56
    POSITIVE LOGITS
     これらの
    0.60
     закона
    0.55
     જો
    0.55
     шко
    0.55
     ваго
    0.54
     термо
    0.54
     riform
    0.54
     щи
    0.53
     ケ
    0.52
    功率
    0.51
    Activations Density 0.000%

    No Known Activations