© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4432
    Prev
    Next
    INDEX
    Explanations

    China and Chinese 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_16k_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
    鸫
    0.85
    菈
    0.84
    堊
    0.82
    螈
    0.80
    铑
    0.80
    鸰
    0.80
    鲽
    0.77
    烔
    0.77
    狨
    0.77
    POSITIVE LOGITS
     Chinese
    1.32
     Confucian
    1.15
     chinese
    1.13
    Chinese
    1.12
     중국
    1.06
     China
    1.04
     китай
    1.00
     Qing
    0.96
     bamboo
    0.93
     चीन
    0.92
    Activations Density 0.303%

    No Known Activations