© 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. 10-GEMMASCOPE-RES-131K
    7. 84506
    Prev
    Next
    INDEX
    Explanations

    Catholic church roles and buildings

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

    This neuron detects mentions of Christian religious denominations, especially “Roman Catholic.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     that
    -2.03
    -"
    -1.52
     it
    -1.51
     from
    -1.41
    ..."
    -1.39
    quido
    -1.37
     theſe
    -1.36
    ...
    -1.34
     also
    -1.32
    couz
    -1.30
    POSITIVE LOGITS
    many
    1.78
    ེད་
    1.45
     fiducia
    1.44
    」、「
    1.42
     pietra
    1.41
     profonda
    1.39
     dipin
    1.38
     chirurgie
    1.34
     ghiaccio
    1.33
     fatica
    1.32
    Activations Density 0.069%

    No Known Activations