© 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. 3643
    Prev
    Next
    INDEX
    Explanations

    code and numbers in contexts

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

    The neuron detects numeric tokens (digits and related punctuation) 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
    medriver
    -0.71
    getSupport
    -0.66
     tao
    -0.65
    ücksich
    -0.65
    tao
    -0.63
    Schema
    -0.62
     rile
    -0.61
    zipCode
    -0.61
     Ninth
    -0.61
     pathway
    -0.61
    POSITIVE LOGITS
    Ỏ
    0.73
    знача
    0.71
    ÍS
    0.71
     案例
    0.65
    猬
    0.65
     салат
    0.64
     העולם
    0.63
     horizon
    0.63
     普通
    0.63
    jm
    0.63
    Activations Density 0.126%

    No Known Activations