© 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. 13337
    Prev
    Next
    INDEX
    Explanations

    The neuron is specialized to detect numeric tokens, especially decimal-formatted 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
     DeFi
    1.01
     Millennials
    0.96
    TikTok
    0.91
     Lâm
    0.88
     প্রতিক্রিয়া
    0.87
     ✨
    0.85
     또는
    0.84
     지속
    0.84
     더
    0.82
     CRISPR
    0.82
    POSITIVE LOGITS
     parameters
    1.20
    参数
    1.00
     Parameters
    0.99
     параметров
    0.94
     abbreviations
    0.94
     параметры
    0.93
     specifications
    0.93
    parameters
    0.88
     rules
    0.87
     numerals
    0.86
    Activations Density 20.398%

    No Known Activations