© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 3985
    Prev
    Next
    INDEX
    Explanations

    SNS symbol and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    瘓
    0.60
    亞洲
    0.53
    鑊
    0.52
    廡
    0.52
    ږئ
    0.49
    癱
    0.48
    經典
    0.47
    劊
    0.47
    晉
    0.46
    ंदीदा
    0.46
    POSITIVE LOGITS
    「
    0.71
     「
    0.69
    ※
    0.68
    ・
    0.68
    ≒
    0.61
     ・
    0.57
    〜
    0.56
     SNS
    0.55
    SNS
    0.54
    ◎
    0.54
    Activations Density 0.040%

    No Known Activations