© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1483
    Prev
    Next
    INDEX
    Explanations

    ( select

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

    variable names and values

    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
     Bedür
    0.54
    <unused94>
    0.52
    gheatmap
    0.52
    kého
    0.52
    URNIZOR
    0.49
    <unused84>
    0.49
     lâm
    0.49
     adhipp
    0.48
     ابن
    0.48
    奈川
    0.47
    POSITIVE LOGITS
    0.63
    ↵
    0.61
    i
    0.59
    <0x0D>
    0.58
    ;
    0.57
    ị
    0.56
    :
    0.56
    '
    0.56
    input
    0.54
    ‘
    0.54
    Activations Density 0.000%

    No Known Activations