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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12494
    Prev
    Next
    INDEX
    Explanations

    and followed by a verb

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

    the neuron detects numeric expressions (tokens representing numbers or numeric values) in the text.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -2.30
     on
    -2.23
     in
    -2.14
     so
    -1.96
     really
    -1.90
     was
    -1.80
    ↵↵↵↵
    -1.73
     that
    -1.65
     which
    -1.64
     even
    -1.63
    POSITIVE LOGITS
    ㍉
    1.77
     fluide
    1.63
     vermel
    1.61
    梣
    1.59
    祤
    1.56
    nexo
    1.55
    莇
    1.55
    saurus
    1.54
     doman
    1.52
    を入れ
    1.52
    Activations Density 0.034%

    No Known Activations