© 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. 150565
    Prev
    Next
    INDEX
    Explanations

    risk and expense, special scheduled, poster tube

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

    AI text generation

    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
     for
    0.61
    es
    0.56
     to
    0.55
     was
    0.54
     M
    0.54
     peter
    0.52
     {
    0.52
     (
    0.51
     layout
    0.51
     $(
    0.51
    POSITIVE LOGITS
     移動
    0.55
     特別
    0.51
    峤
    0.50
     കൈ
    0.50
    opération
    0.50
    क्साइड
    0.49
     情况
    0.49
    Benzoimidazol
    0.49
    Commande
    0.49
    Quan
    0.49
    Activations Density 0.000%

    No Known Activations