© 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. 10213
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens (years, measurements, percentages, decimal numbers).

    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
    s
    1.07
    whitelist
    0.99
    views
    0.90
    ignore
    0.84
    teachers
    0.83
    watchlist
    0.76
     ці
    0.75
    ну
    0.75
     чого
    0.75
    ucci
    0.74
    POSITIVE LOGITS
    ﺤ
    0.93
     Тыва
    0.80
    クター
    0.80
     generado
    0.77
    芰
    0.77
    ITOR
    0.75
     adal
    0.75
     Benoit
    0.75
     Towa
    0.73
     transistor
    0.72
    Activations Density 0.000%

    No Known Activations