© 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. 31-GEMMASCOPE-2-RES-16K
    7. 482
    Prev
    Next
    INDEX
    Explanations

    The neuron specializes in spotting numeric tokens (e.g. years, scores, dollar amounts, percentages) in the text.

    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_31_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
     的
    0.49
    の
    0.49
    的
    0.47
    ﺎ
    0.46
     ห
    0.45
    ǜ
    0.44
     น้ำ
    0.44
    、
    0.44
     乀
    0.44
    <0x11>
    0.43
    POSITIVE LOGITS
     burgeoning
    0.79
     fledgling
    0.70
     venerable
    0.69
     notoriously
    0.67
     hapless
    0.67
     infamous
    0.66
     lucrative
    0.66
     sprawling
    0.66
     storied
    0.66
     multimillion
    0.66
    Activations Density 2.190%

    No Known Activations