© 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. 15614
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

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

    The neuron activates on numeric tokens—especially multi‐digit numbers and decimals—i.e. it finds numerical 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
    Från
    -1.70
     {
    -1.65
     будет
    -1.63
    subsection
    -1.61
    Efter
    -1.59
    咔嚓
    -1.59
     '?
    -1.56
     "`
    -1.51
    ﹶ
    -1.49
    ...?
    -1.48
    POSITIVE LOGITS
     were
    1.69
     whose
    1.61
     who
    1.53
     grossen
    1.51
     géographie
    1.43
     pintadas
    1.43
     people
    1.41
     because
    1.41
     assorted
    1.32
     of
    1.31
    Activations Density 0.011%

    No Known Activations