© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1406
    Prev
    Next
    INDEX
    Explanations

    God made man

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

    The neuron strongly activates on the occurrence of the word “God.”

    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
     měli
    0.60
    ㅋ
    0.54
    参考に
    0.54
     celeb
    0.54
     pensare
    0.53
     měla
    0.53
     faute
    0.52
    صال
    0.52
     traités
    0.52
     hommage
    0.51
    POSITIVE LOGITS
     Himself
    1.42
    祂
    1.04
     Almighty
    0.93
     merciful
    0.90
    赐
    0.89
     تعالیٰ
    0.84
     almighty
    0.84
     mercy
    0.83
    賜
    0.80
     graciously
    0.79
    Activations Density 0.396%

    No Known Activations