© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5027
    Prev
    Next
    INDEX
    Explanations

    The neuron detects numeric tokens (numbers, quantities, or monetary amounts) in the text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    জনিত
    0.73
    рто
    0.70
    朲
    0.70
    MaxIntensity
    0.67
    ColorF
    0.66
    ртом
    0.66
     biota
    0.65
     apoptosis
    0.64
    сора
    0.64
    MORDOR
    0.64
    POSITIVE LOGITS
    แ
    0.69
     decked
    0.68
    cem
    0.66
    petto
    0.65
    كار
    0.65
    avano
    0.63
     خوش
    0.62
    不斷
    0.61
     Town
    0.61
     geçti
    0.61
    Activations Density 0.000%

    No Known Activations