© 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. 75447
    Prev
    Next
    INDEX
    Explanations

    office, trailers, meters

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

    Bob Marley, fact table, Cape Buffalo

    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
    Compiler
    0.55
    said
    0.52
    Mam
    0.48
    such
    0.48
    Rec
    0.47
    A
    0.46
    ISE
    0.44
    As
    0.43
    W
    0.43
     rec
    0.43
    POSITIVE LOGITS
    !:
    0.49
     हमे
    0.49
    !"));
    0.49
     डिसेंबर
    0.48
     माध
    0.47
     }}">
    0.47
     சுக
    0.47
     estaría
    0.46
     कार्ब
    0.46
    লেট
    0.46
    Activations Density 0.000%

    No Known Activations