© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3434
    Prev
    Next
    INDEX
    Explanations

    Chinese culture and philosophy

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongly on mentions of traditional Chinese medicine ingredients and related syndromes.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ቫ
    0.87
    Superhero
    0.86
     جذاب
    0.83
    ━━━━
    0.82
    獪
    0.82
     praticamente
    0.82
    உலகின்
    0.81
    ٬
    0.81
     ইংল্যান্ড
    0.80
    อัล
    0.80
    POSITIVE LOGITS
     Confucian
    1.07
     Dao
    1.03
     imperial
    0.90
     Emperor
    0.88
     Jade
    0.88
     Yuan
    0.87
     Ming
    0.86
     Tao
    0.85
     Guang
    0.84
     dao
    0.84
    Activations Density 0.212%

    No Known Activations