© 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. 8350
    Prev
    Next
    INDEX
    Explanations

    websites and institutions

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

    company names and organizations

    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
    OLYBD
    0.35
    𒁀
    0.35
    禳
    0.34
    Pyrazole
    0.33
     épars
    0.33
    َن
    0.31
    寤
    0.31
     vaginale
    0.31
    颏
    0.31
    㖘
    0.31
    POSITIVE LOGITS
    [
    0.35
    //
    0.33
    ↵
    0.32
     [
    0.32
    i
    0.32
    e
    0.31
    /
    0.31
    u
    0.31
    ’
    0.31
     ...
    0.30
    Activations Density 0.038%

    No Known Activations