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. 7416
    Prev
    Next
    INDEX
    Explanations

    into shorter, groups

    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
    로
    1.25
    क
    1.22
    情况下
    1.20
     से
    1.15
    此
    1.12
     この
    1.05
     của
    1.03
     latter
    1.03
    江苏
    1.02
     این
    1.01
    POSITIVE LOGITS
    শিত
    1.04
     swipe
    0.98
    <unused1872>
    0.95
     sulfonic
    0.93
    sortBy
    0.92
    មី
    0.92
    澳
    0.88
     InputMaybe
    0.88
     wom
    0.88
    expandedTitle
    0.88
    Activations Density 0.712%

    No Known Activations