© 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. 1635
    Prev
    Next
    INDEX
    Explanations

    prayer requests

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

    The neuron activates on words related to prayer (e.g. “pray,” “prayer,” “praying”).

    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
     кухо
    -1.88
    他也
    -1.85
    ⻑
    -1.84
     glittering
    -1.80
     What
    -1.77
    荩
    -1.76
    mbrie
    -1.75
    理由は
    -1.73
     Why
    -1.70
    一定的
    -1.70
    POSITIVE LOGITS
     westfalen
    1.89
     and
    1.84
     tulum
    1.83
     内衣
    1.77
    actress
    1.73
     sandra
    1.72
    fucker
    1.63
     angela
    1.63
     seigneur
    1.62
     monica
    1.62
    Activations Density 0.003%

    No Known Activations