© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99974
    Prev
    Next
    INDEX
    Explanations

    units of measurement

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

    This neuron spotlights measurement terms and units (e.g., metric, arc, vol, nan) that signal numeric quantities or dimensions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -2.47
     a
    -2.19
     At
    -1.71
    /
    -1.68
     in
    -1.66
     on
    -1.63
    t
    -1.61
     it
    -1.51
     as
    -1.50
    :
    -1.48
    POSITIVE LOGITS
    Karakteristik
    1.77
    怍
    1.69
    杪
    1.69
     fotográfica
    1.68
    齪
    1.67
    睒
    1.63
    ーーー
    1.60
    𐤔
    1.55
     organizada
    1.55
     beinahe
    1.55
    Activations Density 0.024%

    No Known Activations