© 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. 15657
    Prev
    Next
    INDEX
    Explanations

    denote, represents, designate

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

    The neuron fires on numeric tokens (especially decimal or integer values) 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
     декабря
    -2.19
     июня
    -1.88
     октября
    -1.70
    餉
    -1.66
    ClInclude
    -1.59
     は
    -1.56
     it
    -1.56
     この
    -1.55
    hline
    -1.55
     января
    -1.54
    POSITIVE LOGITS
    勦
    1.57
    痦
    1.56
    鲣
    1.56
     weitere
    1.55
     the
    1.54
     tiveram
    1.54
     following
    1.51
     verbess
    1.45
    所说的
    1.45
    灕
    1.45
    Activations Density 0.005%

    No Known Activations