© 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. 8578
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by numeric literals—especially floating-point numbers with decimal points—in code.

    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
    Sally
    0.70
    getDescription
    0.67
    getName
    0.66
    ɖ
    0.66
    SERVICE
    0.64
    Vanessa
    0.63
    带来
    0.63
    抱
    0.63
    фессиона
    0.62
    Thông
    0.61
    POSITIVE LOGITS
    for
    1.12
     for
    1.08
     dla
    0.95
     accumulation
    0.91
     dimulai
    0.91
     accum
    0.90
     accumulates
    0.90
     voor
    0.90
     für
    0.89
     для
    0.89
    Activations Density 0.050%

    No Known Activations