© 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. 22-GEMMASCOPE-RES-131K
    7. 434
    Prev
    Next
    INDEX
    Explanations

    Prophet Muhammad, Imam Musa

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

    The neuron detects references to Islamic religious figures and honorific titles (e.g. Prophet, Imam, Allah).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     $
    -1.54
     estos
    -1.28
    .\
    -1.27
     /
    -1.26
    */
    -1.21
     esos
    -1.20
    ",
    -1.19
     THESE
    -1.18
     \
    -1.17
     cujo
    -1.17
    POSITIVE LOGITS
    lový
    1.24
    OLOGICAL
    1.20
     didik
    1.19
     taglia
    1.17
     lancia
    1.16
     wales
    1.15
     hater
    1.14
     nepal
    1.13
     favoriser
    1.13
     tutup
    1.13
    Activations Density 0.004%

    No Known Activations