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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 3653
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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_65k_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
    чению
    0.76
     وتم
    0.73
     dutiful
    0.71
    又是
    0.69
    <unused692>
    0.68
    枯
    0.68
    ولا
    0.67
     garland
    0.67
    quedas
    0.67
    дям
    0.66
    POSITIVE LOGITS
    疎
    0.64
     Î
    0.61
     Sì
    0.60
    то
    0.59
    Ї
    0.58
    यम
    0.56
     tường
    0.56
    ảy
    0.56
    aigu
    0.54
    ـ
    0.54
    Activations Density 0.506%

    No Known Activations