© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 12157
    Prev
    Next
    INDEX
    Explanations

    size measurement

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

    The main thing this neuron does is detect numerical expressions—tokens that represent quantities, measurements, sizes, or 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_24_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
     condizioni
    1.02
    条件
    0.98
     системи
    0.96
     podmín
    0.91
     situazione
    0.89
     situazioni
    0.87
    菪
    0.84
    י
    0.84
    條件
    0.83
     nešto
    0.83
    POSITIVE LOGITS
     diameter
    1.94
     size
    1.85
    尺寸
    1.73
     diameters
    1.70
    diameter
    1.70
    Size
    1.69
    size
    1.65
    Diameter
    1.64
     Size
    1.61
     SIZE
    1.60
    Activations Density 2.726%

    No Known Activations