© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6604
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to numeric tokens—especially decimal numbers or numeric identifiers—wherever they appear 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
    ‌്
    0.64
    Trip
    0.57
    ク
    0.55
    D
    0.54
     Bridg
    0.54
    ٕ
    0.54
    Im
    0.53
    Open
    0.52
     Drought
    0.52
    Big
    0.51
    POSITIVE LOGITS
     corresponds
    1.02
    ”、“
    0.96
     является
    0.96
    是在
    0.93
     aparece
    0.90
     posiada
    0.89
    、
    0.89
    ),(
    0.88
    ）、
    0.86
     appears
    0.85
    Activations Density 0.091%

    No Known Activations