© 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. 45690
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and notation

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

    The neuron fires on numerical quantities and parameters in technical or mathematical contexts (e.g. numbers in equations, decimal values, order/time‐stepping coefficients).

    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
    ଶ
    -1.48
     habari
    -1.45
    伫
    -1.42
    一惊
    -1.32
     damals
    -1.31
    それを
    -1.30
     this
    -1.30
     tohoto
    -1.27
     Kelurahan
    -1.26
    ɗ
    -1.25
    POSITIVE LOGITS
    𓂂
    1.62
    јани
    1.53
    🧫
    1.49
    ׇ
    1.46
    都需要
    1.46
    beyaz
    1.45
     terbatas
    1.38
    我们
    1.35
    érèse
    1.34
     with
    1.33
    Activations Density 0.088%

    No Known Activations