Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7443
    Prev
    Next
    INDEX
    Explanations

    combinations of elements

    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
    м
    2.20
    Д
    1.96
    າ
    1.92
    ૯
    1.90
    ਟ
    1.88
     выражения
    1.73
    entire
    1.73
    гол
    1.70
    an
    1.70
     Miriam
    1.69
    POSITIVE LOGITS
    ro
    2.24
    hops
    2.20
     liel
    2.11
    cie
    2.08
    る
    1.98
    𝙪
    1.97
    indruck
    1.96
    ামুটি
    1.95
    dplyr
    1.94
    rzeć
    1.93
    Activations Density 0.001%

    No Known Activations