© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65530
    Prev
    Next
    INDEX
    Explanations

    Roman Catholic Church

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

    The neuron activates primarily on the phrase “Roman Catholic” (and closely related references to the Roman Catholic Church).

    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
    媖
    -1.85
     aktivitet
    -1.83
    Kedves
    -1.80
    Berat
    -1.76
     bidra
    -1.75
     obtenidos
    -1.74
     caseros
    -1.70
     Strukt
    -1.70
    夕方
    -1.70
     desenli
    -1.67
    POSITIVE LOGITS
     from
    2.03
     to
    2.00
     there
    1.92
     he
    1.89
     We
    1.80
     in
    1.77
     so
    1.75
     it
    1.73
     midst
    1.72
     same
    1.67
    Activations Density 0.006%

    No Known Activations