© 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. 60255
    Prev
    Next
    INDEX
    Explanations

    video content and related actions

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

    short video clips

    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
    ین
    0.77
     in
    0.69
    ONEDB
    0.68
    ק
    0.68
     Films
    0.66
    ร
    0.65
    ח
    0.63
     yattha
    0.63
    ﯽ
    0.62
    도
    0.62
    POSITIVE LOGITS
    c
    0.96
    d
    0.93
    b
    0.88
    /
    0.84
     a
    0.81
    '
    0.79
    z
    0.77
    ка
    0.76
    y
    0.75
    and
    0.75
    Activations Density 0.029%

    No Known Activations