© 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. 133098
    Prev
    Next
    INDEX
    Explanations

    descriptions of actions or states

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

    data proxy interactions

    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
    uene
    0.45
     переста
    0.44
    predicted
    0.44
    凱
    0.43
     السي
    0.43
    bun
    0.43
    wheel
    0.42
    kla
    0.42
    mead
    0.42
    凯
    0.42
    POSITIVE LOGITS
    ANGE
    0.61
     Gagn
    0.53
     ESC
    0.53
     Ons
    0.52
    Ons
    0.52
    VING
    0.51
     Adjacent
    0.51
     escrow
    0.50
     DIAM
    0.50
    ESC
    0.49
    Activations Density 0.000%

    No Known Activations