© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1174
    Prev
    Next
    INDEX
    Explanations

    introduction sections and numbered lists

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

    The neuron detects Bible scripture citations, i.e. sequences denoting book names followed by chapter and verse numbers (e.g. “Matthew 24:1-1…”).

    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
    illas
    -0.83
    opathie
    -0.79
     boj
    -0.78
    clockwise
    -0.78
    ager
    -0.77
     recém
    -0.77
     pochod
    -0.77
     accesibles
    -0.76
     Feldman
    -0.75
    ścić
    -0.75
    POSITIVE LOGITS
    граф
    0.87
     Fakult
    0.81
     drag
    0.75
     тогда
    0.74
     webinars
    0.72
     Watch
    0.71
     watch
    0.71
     Ghar
    0.71
     úl
    0.70
     Museums
    0.70
    Activations Density 0.006%

    No Known Activations