© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 31679
    Prev
    Next
    INDEX
    Explanations

    receiving holy communion

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

    symbolic Christian communion rituals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     Evangel
    0.47
    ेश्वरी
    0.45
     evangel
    0.44
    aggressive
    0.43
    嫐
    0.43
    امه
    0.43
     الأخ
    0.42
     aggressiveness
    0.42
    ക്കാരി
    0.42
     apocalyptic
    0.41
    POSITIVE LOGITS
     communion
    0.59
     ritual
    0.55
    🥖
    0.54
     bread
    0.54
     ceremony
    0.54
     cereal
    0.53
     Communion
    0.52
     Beverage
    0.52
     restaurant
    0.52
     Ceremony
    0.52
    Activations Density 0.028%

    No Known Activations