© 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. 62752
    Prev
    Next
    INDEX
    Explanations

    get a

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

    added here by JavaScript

    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
    ه
    0.54
    <h2>
    0.49
     was
    0.49
    Ass
    0.49
    [
    0.48
     squad
    0.47
    【
    0.47
    Ú
    0.47
     are
    0.47
    Squad
    0.47
    POSITIVE LOGITS
    ierst
    0.57
    llll
    0.50
     चलकर
    0.48
     হিন্দু
    0.47
    llllllll
    0.47
    getStudentNo
    0.46
    idoo
    0.46
    淉
    0.46
     경쟁
    0.45
     जीएसटी
    0.45
    Activations Density 0.000%

    No Known Activations