© 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. 1616
    Prev
    Next
    INDEX
    Explanations

    Islam, Allah

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

    The neuron fires on occurrences of “Allah” (the Islamic name for God).

    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
    囖
    -3.22
    ’
    -3.11
    臜
    -2.95
    毉
    -2.78
    
    -2.66
    
    -2.66
    媜
    -2.64
    i
    -2.63
    腘
    -2.61
    colgante
    -2.56
    POSITIVE LOGITS
    .
    3.39
     There
    2.95
    ти
    2.86
    s
    2.58
    та
    2.56
    к
    2.34
    т
    2.27
    ↵
    2.23
     and
    2.22
     "
    2.19
    Activations Density 0.001%

    No Known Activations