© 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. 22657
    Prev
    Next
    INDEX
    Explanations

    parenthetical clauses and list items

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

    The neuron is specialized to pick out numerical expressions—digits, percentages, and decimal numbers—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
     tradicionais
    -1.46
     píše
    -1.45
     présentent
    -1.36
     voulu
    -1.33
     naturais
    -1.32
     absolut
    -1.31
     especiais
    -1.31
     различных
    -1.30
     specif
    -1.30
     semelhantes
    -1.29
    POSITIVE LOGITS
     all
    1.42
     most
    1.38
     their
    1.30
    }
    1.29
    互联网档案馆
    1.29
     on
    1.25
     help
    1.23
    ）；
    1.20
     a
    1.19
     these
    1.19
    Activations Density 0.130%

    No Known Activations