© 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. 104870
    Prev
    Next
    INDEX
    Explanations

    beginning of descriptive phrases

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

    standard deviation

    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
    که
    0.66
    ↵
    0.61
    FL
    0.59
    ೆಯನ್ನು
    0.57
    APY
    0.57
    ں
    0.57
    ມ
    0.57
    owanych
    0.55
    ,_-
    0.54
    ONSE
    0.54
    POSITIVE LOGITS
     in
    0.88
    在
    0.76
     restaur
    0.59
     for
    0.57
    et
    0.52
     sao
    0.52
     ina
    0.52
     repell
    0.52
     legis
    0.52
     inorder
    0.52
    Activations Density 0.002%

    No Known Activations