© 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. 9559
    Prev
    Next
    INDEX
    Explanations

    width and dimensions

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

    The neuron detects numeric tokens—especially measurements, dimensions, and other technical values (e.g. pixel widths, breakpoints, column counts).

    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
     spacing
    0.65
    Con
    0.59
    Spacing
    0.57
     移動
    0.57
    )_{
    0.56
    adura
    0.56
    OA
    0.55
    igy
    0.54
    Position
    0.53
     カラー
    0.53
    POSITIVE LOGITS
     broadest
    0.67
    narrow
    0.67
     toàn
    0.66
     اغلب
    0.63
     всей
    0.63
     hela
    0.63
    狹
    0.61
    columnwidth
    0.60
     entirety
    0.60
     volled
    0.60
    Activations Density 0.007%

    No Known Activations