© 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. 22-GEMMASCOPE-RES-131K
    7. 130663
    Prev
    Next
    INDEX
    Explanations

    This neuron detects numerical expressions and measurements (e.g. digits, decimal values, lab values, ages, and other numeric data) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    sequential events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     satélite
    -1.08
    abilir
    -0.95
     acomp
    -0.93
    codename
    -0.89
    delivered
    -0.89
    ˍ
    -0.88
    apparently
    -0.85
    accessed
    -0.83
     kadang
    -0.82
    ıza
    -0.82
    POSITIVE LOGITS
     then
    1.70
     therefore
    1.45
     further
    1.43
     subsequently
    1.41
     immediately
    1.32
     thereupon
    1.32
     so
    1.26
     promptly
    1.21
     subsequent
    1.20
     proceed
    1.17
    Activations Density 0.091%

    No Known Activations