© 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. 9053
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find numeric tokens and expressions (e.g. list item numbers, years, and other digits).

    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
    ９
    0.72
    8
    0.68
     ২২
    0.67
    後半
    0.67
    ８
    0.65
    二百
    0.63
     ২৬
    0.61
    9
    0.61
     ২৯
    0.60
     ৬৫
    0.60
    POSITIVE LOGITS
     ১
    1.85
     १
    1.74
     birinci
    1.70
    ১
    1.59
    第一
    1.57
     ১ম
    1.52
    ①
    1.52
    １
    1.51
     ①
    1.48
    ❶
    1.48
    Activations Density 0.436%

    No Known Activations