© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10016
    Prev
    Next
    INDEX
    Explanations

    Gena Lee Nolin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ar
    1.18
    ার
    0.97
    ών
    0.91
    ский
    0.90
    testers
    0.88
    ى
    0.86
    поли
    0.86
     conferred
    0.86
     overshadow
    0.85
    તી
    0.85
    POSITIVE LOGITS
    $('.
    0.93
     zealand
    0.92
    $(".
    0.91
     zakresie
    0.90
     ich
    0.90
    േഷ
    0.89
     hochwert
    0.88
     불구하고
    0.87
     중
    0.87
     Sequelize
    0.85
    Activations Density 0.001%

    No Known Activations