© 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. 2120
    Prev
    Next
    INDEX
    Explanations

    approximately, average, roughly

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

    The neuron detects numeric measurement expressions, especially numbers paired with units (e.g. heights, lengths, weights, temperatures).

    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
     使っ
    0.64
     szczegól
    0.58
     野
    0.58
     言っ
    0.57
     তাহাদিগের
    0.57
    ్రి
    0.57
     {}>,
    0.57
     পড়িল
    0.56
     besondere
    0.55
    ทยา
    0.55
    POSITIVE LOGITS
     maximum
    1.02
     максимум
    1.02
     máximo
    1.00
     depending
    0.95
     excluding
    0.94
     aproximadamente
    0.91
    maximum
    0.90
     maksimum
    0.87
     max
    0.86
     (+
    0.86
    Activations Density 0.612%

    No Known Activations