© 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. 34-GEMMASCOPE-RES-131K
    7. 62547
    Prev
    Next
    INDEX
    Explanations

    numbers in lists

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

    The neuron strongly activates on numeric characters within multi‐digit sequences—especially years (four-digit numbers) and other long numeric strings.

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     eleven
    -0.73
     DOH
    -0.71
    gettext
    -0.71
    IBAction
    -0.69
     cut
    -0.69
    sims
    -0.68
    ámico
    -0.67
    ullan
    -0.67
    LSTM
    -0.67
     spad
    -0.66
    POSITIVE LOGITS
    ｠
    0.91
    Rochester
    0.83
    getRoot
    0.82
    codehaus
    0.81
    oté
    0.80
    oteo
    0.80
     liegenden
    0.80
    μαστε
    0.79
     motoru
    0.78
     Eco
    0.76
    Activations Density 0.016%

    No Known Activations