© 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. 9979
    Prev
    Next
    INDEX
    Explanations

    rule of thumb, three, pareto, thirds

    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
    ل
    2.17
    ל
    2.16
    м
    2.04
    enriched
    1.97
    మయ్య
    1.89
     prestige
    1.62
    なった
    1.61
    erosion
    1.61
    तया
    1.60
    岖
    1.60
    POSITIVE LOGITS
    gea
    1.80
     Lynda
    1.80
    litre
    1.78
    sam
    1.68
    s
    1.67
    tired
    1.67
    drawable
    1.58
    sage
    1.56
    serr
    1.55
    टरनेट
    1.55
    Activations Density 0.003%

    No Known Activations