© 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. 40-GEMMASCOPE-2-RES-262K
    7. 195646
    Prev
    Next
    INDEX
    Explanations

    Chinese and China-related terms

    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
     Вот
    0.44
     ഹിന്ദു
    0.44
     맞
    0.43
     Veamos
    0.42
     FullHD
    0.41
     PLAT
    0.41
     PERFORM
    0.41
     endeavoured
    0.41
    ।...
    0.40
    <unused26>
    0.39
    POSITIVE LOGITS
     চীনা
    0.52
    中国
    0.50
    在中国
    0.50
     中国
    0.48
     چین
    0.48
     Zhao
    0.48
     Shanghai
    0.47
     Chinese
    0.46
     China
    0.46
     china
    0.46
    Activations Density 0.014%

    No Known Activations