© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13578
    Prev
    Next
    INDEX
    Explanations

    spirituality and philosophy

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

    The neuron activates on mentions of Buddhist concepts or figures (e.g. “Buddha,” “Buddhist,” “Dharma,” etc.).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     وه
    0.65
    巫
    0.65
    Dios
    0.65
    鰓
    0.64
    νει
    0.64
    startY
    0.64
    鰯
    0.64
    🧛
    0.62
     расте
    0.61
     காதல்
    0.61
    POSITIVE LOGITS
     Buddhist
    2.16
     Buddhism
    2.06
    Buddhist
    1.98
     Buddhists
    1.91
     buddhist
    1.88
     Buddha
    1.83
     buddha
    1.69
    佛教
    1.67
     buddh
    1.63
     Phật
    1.62
    Activations Density 0.125%

    No Known Activations