© 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. 32812
    Prev
    Next
    INDEX
    Explanations

    `Transmission` or `Jill Dixon` or `panic`

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

    The main thing this neuron does is detect numeric literals (integer tokens) in the text.

    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
     his
    -0.96
     its
    -0.96
     all
    -0.94
     those
    -0.93
     boste
    -0.92
     will
    -0.91
    が広
    -0.90
    sieme
    -0.86
    áis
    -0.86
     Unterstützung
    -0.86
    POSITIVE LOGITS
     seura
    1.01
    kani
    0.94
    rugada
    0.94
    serializers
    0.92
    loài
    0.92
    setopt
    0.91
    Ң
    0.90
    Izzy
    0.90
    yev
    0.89
     осталось
    0.87
    Activations Density 0.001%

    No Known Activations