© 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. 11029
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily activates on numeric tokens or tokens containing digit sequences (i.e., numbers and numbered citations).

    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
    q
    0.96
    G
    0.96
    D
    0.93
    y
    0.91
    Y
    0.91
    A
    0.89
    P
    0.89
    w
    0.87
    ↵
    0.87
    T
    0.86
    POSITIVE LOGITS
     empresario
    0.87
     исследователь
    0.84
     presión
    0.84
     అలా
    0.82
     урав
    0.79
     pressão
    0.79
     inspiración
    0.79
     февраля
    0.78
     основным
    0.77
     избира
    0.76
    Activations Density 0.000%

    No Known Activations