© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16059
    Prev
    Next
    INDEX
    Explanations

    religious vocations

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

    The neuron fires on tokens naming or describing ordained Christian clergy roles (e.g. priest, minister, clergyman, pastor, Reverend).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     namun
    -1.29
    OOO
    -1.23
     ihrem
    -1.22
    P
    -1.20
    づく
    -1.20
     traités
    -1.15
     annoncé
    -1.14
     récents
    -1.13
     \{
    -1.11
    M
    -1.11
    POSITIVE LOGITS
    jā
    1.17
    京城
    1.15
     Nó
    1.13
     in
    1.12
    服务的
    1.09
    ᨆ
    1.06
    geries
    1.05
     superficies
    1.05
    erializer
    1.04
     знали
    1.04
    Activations Density 0.024%

    No Known Activations