© 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. 106329
    Prev
    Next
    INDEX
    Explanations

    Q: How

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

    This neuron responds to tokens that include numeric digits (i.e. any token containing 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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     networking
    -0.96
    edly
    -0.88
     транспорт
    -0.87
    ih
    -0.87
    bat
    -0.87
     buildings
    -0.84
    hir
    -0.84
    elu
    -0.82
    sie
    -0.81
    sied
    -0.81
    POSITIVE LOGITS
    ecido
    0.79
     サンプル
    0.75
     away
    0.74
    Aucun
    0.74
    能在
    0.74
    чивать
    0.73
     gemens
    0.73
    bzw
    0.73
    只有一个
    0.71
    PASO
    0.71
    Activations Density 0.003%

    No Known Activations