© 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. 6869
    Prev
    Next
    INDEX
    Explanations

    Runnable action

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

    function followed by parentheses

    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
    スカート
    0.46
     ích
    0.44
    yczy
    0.44
    膈
    0.42
     সংখ
    0.40
     anticoag
    0.40
    酤
    0.39
     एजेंसियों
    0.39
    دة
    0.39
    許可
    0.38
    POSITIVE LOGITS
     onClick
    0.42
    onClick
    0.42
    ");
    0.39
    itali
    0.39
     प्रारंभ
    0.38
    /");
    0.38
     circle
    0.38
     onPressed
    0.38
     {
    0.38
     ActionListener
    0.38
    Activations Density 0.000%

    No Known Activations