© 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. 68946
    Prev
    Next
    INDEX
    Explanations

    actions after subjects

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

    The neuron strongly activates on words from Biblical narrative passages (e.g. mentions of Jesus, synagogue, James, sick, fever, etc.), effectively detecting scripture 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_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
     this
    -2.36
     you
    -2.25
     your
    -2.08
     our
    -1.92
     will
    -1.73
     my
    -1.67
     currently
    -1.54
     that
    -1.52
     if
    -1.52
     these
    -1.48
    POSITIVE LOGITS
    ebly
    1.44
    淬
    1.43
     was
    1.43
    ܆
    1.40
     bricola
    1.38
    nad
    1.36
    搅拌
    1.31
     gewöhnlich
    1.31
     autonomie
    1.31
    nade
    1.29
    Activations Density 0.020%

    No Known Activations