© 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. 14788
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens and digit sequences (e.g. phone numbers, years, codes).

    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
    的日子
    0.61
     Acids
    0.59
    Analytics
    0.58
     शुरुआत
    0.57
    폴
    0.57
    Blogs
    0.57
     оно
    0.57
     হলিউ
    0.57
     Shirts
    0.57
     혼
    0.56
    POSITIVE LOGITS
    ätzung
    0.67
    upam
    0.66
     attent
    0.63
    ał
    0.63
     मूल्या
    0.62
     equivariant
    0.60
    ակի
    0.59
     percep
    0.59
     clamps
    0.58
    ynchus
    0.58
    Activations Density 0.001%

    No Known Activations