© 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. 11459
    Prev
    Next
    INDEX
    Explanations

    religions and their associated concepts

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

    The neuron strongly responds to occurrences of the word “Christian” (and closely related religious proper‐noun mentions).

    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
     phổi
    0.62
     branchNode
    0.61
     религиоз
    0.61
    ᐋ
    0.59
     Catholicism
    0.58
     মসজিদে
    0.58
    Swami
    0.57
    पीसी
    0.56
     مسجد
    0.55
    NIC
    0.55
    POSITIVE LOGITS
     Dior
    0.83
     dior
    0.63
    eing
    0.60
     helt
    0.60
     Doppler
    0.60
     dunes
    0.59
    ⌬
    0.59
     connotations
    0.58
     celery
    0.57
     bisc
    0.56
    Activations Density 0.108%

    No Known Activations