© 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. 19663
    Prev
    Next
    INDEX
    Explanations

    asynchronous tasks

    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
    АО
    0.50
    敵
    0.47
    Cached
    0.47
    拈
    0.46
    我不
    0.46
    raded
    0.46
    庖
    0.45
    coded
    0.45
    敌
    0.45
    我覺得
    0.44
    POSITIVE LOGITS
    el
    0.46
    emark
    0.45
     pueblo
    0.45
     for
    0.45
     मार्शल
    0.44
     insurer
    0.44
     D
    0.43
    منٹ
    0.42
    ing
    0.42
     হুই
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.