© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25001
    Prev
    Next
    INDEX
    Explanations

    onCreate, report, initially

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

    The neuron fires on numeric tokens—especially those with decimal points—such as version numbers, dosages, or other measurements.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ~\
    -0.95
    strokes
    -0.93
     "|"
    -0.84
     TRANSFORM
    -0.84
    👌
    -0.84
     ("\
    -0.83
     """
    -0.80
     pthread
    -0.79
     Hauses
    -0.79
     operación
    -0.78
    POSITIVE LOGITS
    嫦
    0.90
     initially
    0.84
     unspecified
    0.84
    nical
    0.82
    auen
    0.81
    argento
    0.81
     múltip
    0.80
    チューム
    0.79
     initial
    0.79
    WebpackPlugin
    0.78
    Activations Density 0.050%

    No Known Activations