© 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. 31-GEMMASCOPE-2-RES-65K
    7. 5714
    Prev
    Next
    INDEX
    Explanations

    Korean peninsula and culture

    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_31_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
    译
    0.50
    Injury
    0.49
    受伤
    0.48
    过程
    0.47
    亚马
    0.46
    丏
    0.46
    蒉
    0.46
    穵
    0.46
    炁
    0.46
     Injury
    0.45
    POSITIVE LOGITS
     Pyongyang
    0.95
     Korean
    0.79
     Korea
    0.77
     kimchi
    0.75
     Seoul
    0.73
     korea
    0.69
    朝鲜
    0.68
     조선
    0.68
    朝鮮
    0.66
     korean
    0.65
    Activations Density 0.017%

    No Known Activations