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. 1698
    Prev
    Next
    INDEX
    Explanations

    mathematical parentheses and function calls

    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
     Wilkes
    0.57
     divisional
    0.57
     downright
    0.57
    >×</
    0.55
    ⴱ
    0.54
     gange
    0.54
     Appeals
    0.53
     [:
    0.53
     ぐらい
    0.52
     knees
    0.52
    POSITIVE LOGITS
    mathrm
    0.89
    text
    0.88
    mathcal
    0.74
     text
    0.74
    mathbf
    0.73
    alpha
    0.73
    operatorname
    0.71
    frac
    0.67
    mathbb
    0.66
    mathfrak
    0.66
    Activations Density 0.015%

    No Known Activations