© 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. 11561
    Prev
    Next
    INDEX
    Explanations

    discounts and percentages

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

    This neuron activates on numeric tokens—digits, multi‐digit numbers, percentages, prices, and other numeric amounts—in promotional or coupon 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
     and
    -1.87
     I
    -1.84
     had
    -1.72
     C
    -1.67
     P
    -1.66
     D
    -1.66
     p
    -1.62
     G
    -1.59
     S
    -1.55
     M
    -1.53
    POSITIVE LOGITS
     your
    1.95
    ḿ
    1.71
     gouttes
    1.67
    笑了笑
    1.66
     disebutkan
    1.66
    굼
    1.66
     cliquer
    1.65
     envoyer
    1.63
     VIDEOT
    1.63
    に於
    1.63
    Activations Density 0.190%

    No Known Activations