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. 29-GEMMASCOPE-2-RES-262K
    4. 52777
    Prev
    Next
    INDEX
    Explanations

    model generation

    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_29_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
    开启
    0.74
    懈
    0.73
     เล
    0.73
     cancellation
    0.68
    開啟
    0.67
     Cancellation
    0.65
    眨
    0.64
    切れ
    0.64
     interval
    0.64
     Periods
    0.63
    POSITIVE LOGITS
    ErrorBoundary
    0.65
     Guten
    0.64
    мат
    0.63
    شته
    0.63
    amiliar
    0.62
    intr
    0.61
    msubsup
    0.61
    ங்களுடன்
    0.61
    Gand
    0.60
    lossen
    0.60
    Activations Density 0.007%

    No Known Activations