© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109014
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    The neuron activates on numeric tokens—years, counts, ratings, monetary figures, crowd sizes, etc.—i.e. anything containing digits.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rigado
    -0.80
    ➗
    -0.76
    節約
    -0.73
     halaman
    -0.72
     liczba
    -0.72
    ⃟
    -0.71
    athie
    -0.71
    ^{-}
    -0.71
    ʋ
    -0.70
    PAREN
    -0.69
    POSITIVE LOGITS
    reps
    0.82
    arskie
    0.81
     mówi
    0.80
    Excerpts
    0.80
    施工
    0.79
    =[
    0.77
     injec
    0.77
    Accademia
    0.77
     Pill
    0.76
     Angles
    0.76
    Activations Density 0.002%

    No Known Activations