© 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. 13419
    Prev
    Next
    INDEX
    Explanations

    size or quantity

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

    The neuron detects numeric measurement expressions (quantities with units, dimensions, sizes, fractions).

    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
    injured
    0.63
    cel
    0.55
    setC
    0.54
    帚
    0.54
    ló
    0.53
    lp
    0.53
    inel
    0.53
    代引
    0.52
    chnitten
    0.50
     場合
    0.50
    POSITIVE LOGITS
     ¼
    0.93
     mm
    0.92
     millimeter
    0.84
     MM
    0.83
     мм
    0.82
    ｍｍ
    0.78
    mm
    0.76
    MM
    0.75
     millimeters
    0.74
    Tiny
    0.73
    Activations Density 0.151%

    No Known Activations