© 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. 38941
    Prev
    Next
    INDEX
    Explanations

    opens new window or popup

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

    problematic misunderstood, Open menu

    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
     »
    0.41
     ©
    0.41
    মার
    0.41
     offensive
    0.41
     ”
    0.40
    burn
    0.39
     Welsh
    0.39
     Burmese
    0.39
     バ
    0.39
    เทพ
    0.39
    POSITIVE LOGITS
    ссов
    0.49
    QUIN
    0.47
    ገለ
    0.45
    含有
    0.45
    ಿನಿ
    0.44
    гин
    0.43
    ән
    0.43
    quin
    0.42
    っこ
    0.41
    лка
    0.41
    Activations Density 0.001%

    No Known Activations