© 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. 106326
    Prev
    Next
    INDEX
    Explanations

    chart data structure keywords

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

    The neuron detects tokens that are purely numeric literals (sequences of digits).

    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
     länder
    -0.81
    ellus
    -0.75
    ~,
    -0.73
    behälter
    -0.72
     Dessa
    -0.72
     Detta
    -0.72
     va
    -0.71
    nesses
    -0.70
     ath
    -0.70
    istory
    -0.69
    POSITIVE LOGITS
    רְ
    0.79
     fraudulent
    0.76
    csc
    0.75
    Horace
    0.73
    name
    0.71
     data
    0.69
     violência
    0.69
     trouxe
    0.68
    data
    0.68
     setName
    0.67
    Activations Density 0.016%

    No Known Activations