© 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. 14054
    Prev
    Next
    INDEX
    Explanations

    chinese text and entities

    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
    銠
    0.90
    螫
    0.89
    堊
    0.88
    鲔
    0.87
    蓣
    0.86
    鳟
    0.86
    睪
    0.85
    鐒
    0.84
    爌
    0.83
    蕈
    0.82
    POSITIVE LOGITS
     Chinese
    1.13
     Beijing
    1.01
     zhong
    0.96
     चीन
    0.95
     yuan
    0.95
     chinese
    0.93
     China
    0.90
    baidu
    0.90
     Chengdu
    0.89
     xia
    0.89
    Activations Density 0.031%

    No Known Activations