© 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. 128936
    Prev
    Next
    INDEX
    Explanations

    les followed by French nouns

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

    This neuron fires on the French definite article “les” (often capitalized as “Les”).

    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
     
    -2.77
     звезды
    -2.58
    岨
    -2.56
    ⼗
    -2.56
     offre
    -2.50
    锨
    -2.48
    ፨
    -2.44
    婓
    -2.31
    Mainly
    -2.31
    ⦊
    -2.30
    POSITIVE LOGITS
     one
    3.20
     from
    3.13
     two
    2.95
     three
    2.72
     These
    2.67
     remarkable
    2.66
    雋
    2.63
    好吗
    2.59
    法规
    2.56
    after
    2.55
    Activations Density 0.001%

    No Known Activations