© 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-262K
    7. 15151
    Prev
    Next
    INDEX
    Explanations

    Korea, Korean culture, history

    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_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
    鹕
    0.67
     Nicar
    0.60
    高志森
    0.59
    烃
    0.58
    Arkansas
    0.57
    蜢
    0.57
    Florida
    0.57
    ឡិច
    0.57
    Orlando
    0.56
    鐟
    0.56
    POSITIVE LOGITS
     Korean
    1.82
     Korea
    1.77
     korean
    1.63
     korea
    1.60
    Korean
    1.59
     한국
    1.58
     Seoul
    1.57
     Koreans
    1.55
    韩国
    1.54
    韓國
    1.48
    Activations Density 0.100%

    No Known Activations