© 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. 168990
    Prev
    Next
    INDEX
    Explanations

    candidate, successful, for

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

    cultural concepts and events

    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
    f
    0.55
    rote
    0.49
    you
    0.48
    追求
    0.47
    เซีย
    0.46
    r
    0.46
    ouncing
    0.45
    tablename
    0.44
     co
    0.44
     denial
    0.43
    POSITIVE LOGITS
    ام
    0.52
     Mushroom
    0.49
     ইনিংস
    0.49
    ℗
    0.49
    ад
    0.48
    لاك
    0.47
    credits
    0.46
     продукта
    0.46
     Callable
    0.46
    럼
    0.46
    Activations Density 0.000%

    No Known Activations