© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9212
    Prev
    Next
    INDEX
    Explanations

    ellipsis and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numeric tokens—especially quantities, measurements, prices, dates, and other figures with units.

    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
     جوسینو
    0.62
    চলিত
    0.60
     socalled
    0.59
     dukkham
    0.57
     pavatt
    0.54
    Ī
    0.52
    ീല
    0.49
    നെയും
    0.48
     puriso
    0.48
    ेशनों
    0.46
    POSITIVE LOGITS
    ...
    4.22
     ...
    4.03
    …
    3.86
    ....
    3.81
    ・・・
    3.73
    ...?
    3.69
    ......
    3.66
    .....
    3.64
    \...
    3.53
     ....
    3.52
    Activations Density 1.056%

    No Known Activations