© 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. 41403
    Prev
    Next
    INDEX
    Explanations

    God

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

    The main thing this neuron does is detect mentions of God (and equivalent divine names) across different languages.

    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
    赑
    -1.97
    뮐
    -1.88
    苼
    -1.85
    虓
    -1.83
    臜
    -1.78
    ...'
    -1.72
     accessori
    -1.69
    TintMode
    -1.69
    
    -1.67
    </>
    -1.66
    POSITIVE LOGITS
    {
    2.11
    .
    2.03
     it
    1.78
    ↵↵
    1.75
     while
    1.69
     wiederhol
    1.65
    <b>
    1.58
     —
    1.56
     ‘‘
    1.54
     a
    1.52
    Activations Density 0.022%

    No Known Activations