© 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. 34-GEMMASCOPE-RES-131K
    7. 103402
    Prev
    Next
    INDEX
    Explanations

    most gracious, Reverend, Glorious

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

    The neuron strongly activates on liturgical or prayer‐style language, especially archaic/formal invocations (e.g. Catholic prayer text).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    🚤
    -0.78
    флек
    -0.74
     simpler
    -0.73
    🛥
    -0.71
     additional
    -0.71
     existing
    -0.71
    additional
    -0.70
    不明白
    -0.70
    وازم
    -0.69
    largest
    -0.67
    POSITIVE LOGITS
     holy
    2.13
     blessed
    2.00
     honorable
    1.98
     noble
    1.89
     esteemed
    1.82
     honourable
    1.80
     revered
    1.78
     august
    1.77
     sacred
    1.73
     honored
    1.68
    Activations Density 0.055%

    No Known Activations