© 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. 6831
    Prev
    Next
    INDEX
    Explanations

    numbers following `1`, `2`

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

    The neuron strongly activates on numeric tokens, i.e. standalone digits or 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
     on
    -2.34
     for
    -2.25
     not
    -2.03
     in
    -1.89
     first
    -1.79
     good
    -1.77
     mostly
    -1.73
     most
    -1.72
     as
    -1.70
     more
    -1.70
    POSITIVE LOGITS
    ➀
    1.76
    骉
    1.64
     inan
    1.63
     perak
    1.63
     MIK
    1.61
     vard
    1.60
    ◼
    1.60
     ANAL
    1.60
     hatt
    1.59
     Nisan
    1.59
    Activations Density 0.190%

    No Known Activations