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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 2122
    Prev
    Next
    INDEX
    Explanations

    parentheses, punctuation, and code literals

    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_17_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
     hypothetical
    0.56
    W
    0.55
     Euclidean
    0.54
     hinn
    0.54
    H
    0.54
    ធាតុ
    0.52
    X
    0.52
     differing
    0.52
    Y
    0.51
     different
    0.50
    POSITIVE LOGITS
     (!
    0.64
    溂
    0.63
    ⦕
    0.63
    <unused2184>
    0.63
     baseApiPath
    0.61
     minifyEnabled
    0.61
     chromedp
    0.57
    ၊
    0.57
    おしゃれ
    0.56
    <unused762>
    0.56
    Activations Density 0.662%

    No Known Activations