© 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. 10149
    Prev
    Next
    INDEX
    Explanations

    religious doctrines and creeds

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

    The neuron activates on mentions of the Vatican or the Pope and related official church news (e.g. “VATICAN CITY,” “Pope Francis,” “continuity of the church,” 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
     preachers
    0.66
     ఆధ్యాత్మిక
    0.61
     religiosas
    0.61
     temptations
    0.59
    槁
    0.59
     आध्यात्मिक
    0.59
     preacher
    0.58
    鯤
    0.58
    lmfit
    0.58
     sermons
    0.57
    POSITIVE LOGITS
     papal
    1.20
    Pope
    1.16
     Vatican
    1.13
     pope
    1.13
     Pope
    1.05
     pap
    0.98
    Pap
    0.98
    pap
    0.97
     cardinals
    0.97
     पोप
    0.96
    Activations Density 0.172%

    No Known Activations