© 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. 10-GEMMASCOPE-RES-131K
    7. 101040
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, and times

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

    The neuron fires on numeric tokens—especially decimal numbers (floating-point 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
     HIEROGLYPH
    -1.62
     prevista
    -1.62
    either
    -1.55
     Comuni
    -1.55
    Etape
    -1.54
     PUST
    -1.53
    Sommaire
    -1.52
     CALIFORN
    -1.50
     však
    -1.49
    Exemple
    -1.49
    POSITIVE LOGITS
     where
    1.65
     ↓,
    1.38
     autre
    1.37
     poteva
    1.35
     rer
    1.34
    ,”
    1.33
     -
    1.33
    ↵
    1.32
     unos
    1.29
     faceva
    1.27
    Activations Density 0.041%

    No Known Activations