© 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. 10-GEMMASCOPE-RES-131K
    7. 38345
    Prev
    Next
    INDEX
    Explanations

    xml declaration

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

    The neuron detects numeric literals (numbers, including integers and decimals) 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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     by
    -2.34
     while
    -1.88
     for
    -1.84
     because
    -1.80
     when
    -1.80
     as
    -1.80
     through
    -1.70
     Usually
    -1.70
     during
    -1.70
     Every
    -1.70
    POSITIVE LOGITS
    ⎔
    1.73
     viejos
    1.60
     delightful
    1.60
     clásicos
    1.56
     dubbel
    1.55
     guapos
    1.55
    ཌ
    1.55
    孭
    1.55
     nieuwe
    1.54
     creativos
    1.54
    Activations Density 0.008%

    No Known Activations