© 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. 17079
    Prev
    Next
    INDEX
    Explanations

    Chinese language 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
    蓿
    0.69
    蓣
    0.63
    鲽
    0.62
     blanchâtre
    0.62
    堊
    0.61
    鳕
    0.60
    狨
    0.59
    螫
    0.58
    蝰
    0.58
    飓
    0.57
    POSITIVE LOGITS
     Chinese
    2.05
    Chinese
    1.87
     중국
    1.80
     китай
    1.79
     China
    1.75
     chinese
    1.75
     चीन
    1.64
    China
    1.62
     চীনা
    1.60
     Beijing
    1.55
    Activations Density 0.443%

    No Known Activations