© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10623
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens—especially dates, years, counts, and similar statistical or numbered expressions.

    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
    PATHS
    0.73
    ৭
    0.72
    巴
    0.71
    з
    0.71
    管理
    0.71
    文献
    0.70
    Н
    0.69
     मांझी
    0.69
    מק
    0.69
    Вот
    0.67
    POSITIVE LOGITS
    ette
    1.01
    mers
    0.95
    nama
    0.94
    <0x80>
    0.85
    te
    0.85
    ası
    0.84
    it
    0.82
    mL
    0.82
    ns
    0.82
    ্বরূপ
    0.81
    Activations Density 8.178%

    No Known Activations