© 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. 130643
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens (e.g. quantities, prices, dates, IDs), effectively detecting numbers in the text.

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

    total amount, calculation, or financial summary

    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
     filós
    -0.99
    に挑戦
    -0.93
     грамм
    -0.91
    vocations
    -0.91
     gặp
    -0.90
    reichen
    -0.88
     demanda
    -0.87
    стов
    -0.87
    を選び
    -0.86
    も同じ
    -0.86
    POSITIVE LOGITS
     final
    1.31
     then
    1.24
     culminating
    1.18
     finale
    1.16
    MessageTagHelper
    1.14
     total
    1.09
     getTotal
    1.08
    Final
    1.08
     Final
    1.04
     climax
    1.03
    Activations Density 0.002%

    No Known Activations