© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 19183
    Prev
    Next
    INDEX
    Explanations

    parentheses or brackets

    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_22_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
    予想
    0.72
    安全性
    0.72
     安全
    0.71
    ﹁
    0.69
    ="'.$
    0.68
    ^{+},
    0.68
     Smartphone
    0.67
    ='".$
    0.67
     უფრო
    0.66
    思議
    0.66
    POSITIVE LOGITS
     whipped
    0.72
     sprinkled
    0.70
    blocks
    0.69
    (
    0.69
    ümüş
    0.69
    heads
    0.69
     мира
    0.68
     Til
    0.68
    AME
    0.67
    ama
    0.67
    Activations Density 0.002%

    No Known Activations