© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 6473
    Prev
    Next
    INDEX
    Explanations

    China-related places and business

    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
    秏
    0.66
    鎊
    0.63
    齬
    0.62
    荽
    0.61
    轵
    0.61
    獧
    0.60
    樎
    0.58
    秵
    0.57
    釹
    0.56
    사용
    0.56
    POSITIVE LOGITS
     Beijing
    0.89
     China
    0.86
     Chinese
    0.85
     Zhejiang
    0.82
     중국
    0.80
     चीन
    0.79
     Shenzhen
    0.78
     Nanjing
    0.75
     Chongqing
    0.74
     Jiangsu
    0.73
    Activations Density 0.003%

    No Known Activations