© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15477
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens—especially floating‐point or high‐precision 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
     demasi
    0.79
     comandos
    0.78
     ejercer
    0.78
     ماهی
    0.77
    ް
    0.76
    𒅗
    0.75
    ।’
    0.75
    ใ
    0.73
     evaluar
    0.73
    Reasoner
    0.73
    POSITIVE LOGITS
     troupe
    0.95
     Furthermore
    0.68
    taining
    0.66
     punctuation
    0.66
    0.66
     cir
    0.63
     desperate
    0.63
     hastily
    0.63
    _[
    0.62
     wrought
    0.62
    Activations Density 0.000%

    No Known Activations