© 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. 68495
    Prev
    Next
    INDEX
    Explanations

    sale of 252,423 of the album’s

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

    The neuron activates on numeric characters (digits) in the text—that is, it detects 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
     and
    -2.17
     that
    -2.00
     your
    -1.69
     then
    -1.66
     Then
    -1.54
     with
    -1.52
     you
    -1.47
    子ども
    -1.39
     затем
    -1.38
     entonces
    -1.38
    POSITIVE LOGITS
     lança
    1.75
    schwar
    1.59
     úl
    1.52
    葙
    1.50
     contraire
    1.47
    Oye
    1.44
    Hozzá
    1.43
     paulista
    1.41
     intitu
    1.39
     judicia
    1.38
    Activations Density 0.223%

    No Known Activations