© 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. 64410
    Prev
    Next
    INDEX
    Explanations

    child electrode

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

    The neuron consistently fires on numeric literals (integers or decimals), i.e. tokens representing numbers.

    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
     dopln
    -0.89
     Braut
    -0.88
     къде
    -0.88
     glück
    -0.85
     ventilation
    -0.82
    GoogleApiClient
    -0.81
    xac
    -0.81
     kép
    -0.81
     Finance
    -0.80
     ludzi
    -0.78
    POSITIVE LOGITS
    ♡♡
    0.95
     ウェ
    0.91
    quanto
    0.90
     Omer
    0.84
     Basso
    0.84
    Перед
    0.83
    האם
    0.82
     then
    0.82
     prevede
    0.81
    ebabkan
    0.81
    Activations Density 0.002%

    No Known Activations