© 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. 83906
    Prev
    Next
    INDEX
    Explanations

    numbers or measurements

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

    This neuron activates on numeric tokens, especially multi-digit 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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     marchandises
    -1.80
     jeux
    -1.58
    rás
    -1.52
    跸
    -1.46
     forêts
    -1.44
     producteur
    -1.42
     créativité
    -1.41
    krieg
    -1.41
     เร
    -1.40
     farine
    -1.39
    POSITIVE LOGITS
     two
    1.72
    𖧧
    1.42
     three
    1.41
    𖥸
    1.41
     administracy
    1.38
     setelah
    1.38
     very
    1.37
     theoretically
    1.35
     most
    1.34
     as
    1.33
    Activations Density 0.053%

    No Known Activations