© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3503
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to mentions of deities or religious figures (e.g. “Allah,” “God,” Peter, Timothy).

    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_24_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
    ’
    0.90
    ায়ার
    0.78
    Family
    0.77
    摘要
    0.74
     лен
    0.72
    传说
    0.72
    転
    0.72
    Health
    0.70
    witch
    0.70
    inkle
    0.69
    POSITIVE LOGITS
    ו
    0.89
    UTONIUM
    0.86
    وو
    0.79
     любит
    0.77
     enjoined
    0.77
     медве
    0.76
     главный
    0.76
    o
    0.76
     сообщил
    0.74
     indignant
    0.74
    Activations Density 0.001%

    No Known Activations