© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117484
    Prev
    Next
    INDEX
    Explanations

    label followed by 1

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

    This neuron detects Bible‐style scripture references, in particular “Book Chapter:Verse” citations (e.g. “John 3:16”).

    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
    淨
    -0.91
    تاح
    -0.86
     市
    -0.85
     would
    -0.85
     پیشن
    -0.83
     varit
    -0.79
     kini
    -0.78
    Would
    -0.78
    تل
    -0.78
    endforeach
    -0.77
    POSITIVE LOGITS
    Rr
    0.84
     strait
    0.79
     sayings
    0.78
    に入り
    0.76
     mediocre
    0.76
     impromptu
    0.75
    arne
    0.74
    price
    0.74
     incre
    0.73
     GAO
    0.72
    Activations Density 0.002%

    No Known Activations