© 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. 31-GEMMASCOPE-2-RES-65K
    4. 11709
    Prev
    Next
    INDEX
    Explanations

    Java Spring Boot Chinese

    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
    鲔
    0.88
    鏻
    0.79
    镤
    0.76
    磧
    0.75
    酲
    0.73
    䓶
    0.73
    辂
    0.72
    轺
    0.72
    堊
    0.71
    缬
    0.70
    POSITIVE LOGITS
     Chinese
    0.77
    mybatis
    0.75
     chinese
    0.72
     WeChat
    0.71
     yuan
    0.70
     Shanghai
    0.68
    springboot
    0.68
    alibaba
    0.68
     
    0.68
    ,
    0.68
    Activations Density 0.013%

    No Known Activations