© 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. 41014
    Prev
    Next
    INDEX
    Explanations

    grasping or saying

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

    product lifecycle

    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
    is
    0.52
    n
    0.52
    d
    0.48
     kjø
    0.47
    haltung
    0.47
    ;";
    0.46
    th
    0.46
    इसी
    0.46
     kú
    0.46
     মাই
    0.45
    POSITIVE LOGITS
    antees
    0.48
    лением
    0.44
    😷
    0.43
    ালেন
    0.43
    ‌లు
    0.42
    👎
    0.42
    ptăm
    0.42
     Sacrifice
    0.41
     activates
    0.41
    ിക്കേണ്ട
    0.41
    Activations Density 0.000%

    No Known Activations