© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21518
    Prev
    Next
    INDEX
    Explanations

    in, at, by, with, as, under

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

    The neuron is detecting decimal numbers (numeric values containing a decimal point) in the text.

    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
     which
    -2.39
     của
    -1.75
          
    -1.63
     essas
    -1.62
     that
    -1.57
     you
    -1.55
           
    -1.52
     nejlepší
    -1.52
    譏
    -1.48
       
    -1.48
    POSITIVE LOGITS
     setCode
    1.41
    另一
    1.40
     bordir
    1.39
     sorts
    1.38
     bogotá
    1.37
     anunció
    1.35
    よね
    1.33
     caballeros
    1.32
    高温
    1.31
     geändert
    1.30
    Activations Density 0.248%

    No Known Activations