© 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. 7489
    Prev
    Next
    INDEX
    Explanations

    capacity

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

    The main thing this neuron does is detect numeric expressions—tokens representing numbers, quantities, prices, dates, or other numeric measurements.

    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
    Libraries
    0.58
    libraries
    0.54
     অবলম্বন
    0.52
     reich
    0.52
    Series
    0.51
    宒
    0.49
    getFlight
    0.49
     libraries
    0.49
    series
    0.48
    嫁
    0.46
    POSITIVE LOGITS
     capacity
    1.95
     Capacity
    1.88
     CAPACITY
    1.87
    人数
    1.85
    Capacity
    1.83
    人數
    1.80
    capacity
    1.77
     kapasitas
    1.76
     capacidad
    1.70
    容量
    1.70
    Activations Density 0.450%

    No Known Activations