© 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. 62423
    Prev
    Next
    INDEX
    Explanations

    string or Str data types

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

    The neuron activates on numeric tokens (strings of digits) 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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    レギュラー
    -0.90
     jesus
    -0.88
    每一个
    -0.80
    少なくとも
    -0.80
     fatta
    -0.79
    اعمال
    -0.77
    Від
    -0.77
    提现
    -0.75
    感的
    -0.75
    ジャン
    -0.74
    POSITIVE LOGITS
     here
    1.13
     string
    0.98
     meille
    0.95
    string
    0.89
     bool
    0.89
    朝
    0.86
    enson
    0.85
    ]==
    0.84
    RotationOrder
    0.83
     cyclisme
    0.83
    Activations Density 0.008%

    No Known Activations