© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11437
    Prev
    Next
    INDEX
    Explanations

    Chinese history and Confucianism

    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_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
    輥
    0.67
    蜞
    0.66
    狨
    0.66
     Umsatz
    0.66
    猞
    0.66
    銠
    0.64
    瀘
    0.64
    莳
    0.64
    鸰
    0.64
    蜢
    0.63
    POSITIVE LOGITS
     Chinese
    0.77
     Confucian
    0.74
     chinese
    0.68
     중국
    0.65
     China
    0.64
     Dao
    0.63
     китай
    0.59
     wei
    0.58
     Shang
    0.57
     bamboo
    0.57
    Activations Density 0.031%

    No Known Activations