© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12511
    Prev
    Next
    INDEX
    Explanations

    The neuron chiefly activates on numeric tokens and digit sequences—years, version numbers, dates, counts, and similar numerical expressions.

    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
     provenant
    0.63
     recirculation
    0.63
     barbaric
    0.61
     сель
    0.59
     roam
    0.57
    ל
    0.57
    嘹
    0.57
     purported
    0.57
    ऎ
    0.57
    如果我们
    0.56
    POSITIVE LOGITS
     얘기를
    0.70
    gefühl
    0.67
     Bunu
    0.63
    வும்
    0.62
     Detalles
    0.61
    ceği
    0.59
    pannt
    0.57
    ceğini
    0.57
    いを
    0.57
    oing
    0.56
    Activations Density 6.716%

    No Known Activations