© 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. 89282
    Prev
    Next
    INDEX
    Explanations

    events, stories, or states

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

    adjective endings, specific lengths

    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
    ↵↵
    0.54
    for
    0.54
    a
    0.53
     {
    0.51
    {
    0.50
    ?
    0.48
    ה
    0.48
    .
    0.46
    .{
    0.46
     (§
    0.46
    POSITIVE LOGITS
     vuttam
    0.52
     synagogues
    0.52
    atthanam
    0.52
     ακόμα
    0.52
    avkhat
    0.51
     पहुंची
    0.50
     crevices
    0.50
    <unused65>
    0.50
    চলে
    0.49
    schod
    0.49
    Activations Density 0.001%

    No Known Activations