© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13409
    Prev
    Next
    INDEX
    Explanations

    Zen Buddhism

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    姬
    0.71
     Nawab
    0.63
     mythological
    0.56
     Manipur
    0.56
    להקה
    0.55
    ⌣
    0.55
     regalías
    0.54
     cyclone
    0.53
    굼
    0.53
     মিষ্টি
    0.51
    POSITIVE LOGITS
     Zen
    0.74
     Keg
    0.73
     Tend
    0.70
    Keg
    0.70
     Foy
    0.69
    Zen
    0.67
     Pure
    0.66
     Soto
    0.66
     sect
    0.64
     zen
    0.64
    Activations Density 0.031%

    No Known Activations