© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10732
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric tokens—especially decimal numbers or percentages—i.e. it detects quantitative data in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    َد
    0.82
    誣
    0.77
    executeUpdate
    0.77
    expiration
    0.74
    譏
    0.73
    unteers
    0.73
    вою
    0.71
    лама
    0.71
    誹
    0.71
    लोनी
    0.71
    POSITIVE LOGITS
     region
    0.98
     Category
    0.97
     anthropogenic
    0.96
     Region
    0.95
     Kategorie
    0.93
     category
    0.90
     kategorie
    0.90
     Categories
    0.89
     Table
    0.85
     Gruppe
    0.85
    Activations Density 0.063%

    No Known Activations