© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7999
    Prev
    Next
    INDEX
    Explanations

    book titles and subtitles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Villas
    0.30
     Scott
    0.30
     Rihanna
    0.30
     James
    0.28
     Bak
    0.27
     Hughes
    0.27
     Blau
    0.27
    <strong>
    0.27
     Ryan
    0.27
     Williams
    0.27
    POSITIVE LOGITS
    <unused1092>
    0.52
    <unused549>
    0.49
    <unused277>
    0.49
    <unused997>
    0.49
    <unused1089>
    0.49
    <unused428>
    0.49
    <unused525>
    0.48
    <unused646>
    0.48
    <unused432>
    0.48
    <unused729>
    0.48
    Activations Density 0.000%

    No Known Activations