© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91650
    Prev
    Next
    INDEX
    Explanations

    French proper nouns with definite articles

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

    This neuron strongly activates on the French plural article “des” (and similar French articles like “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_34/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
    を
    -1.20
     上
    -1.07
    は
    -1.03
    または
    -1.01
    <bos>
    -1.01
    錐
    -0.96
    hiva
    -0.96
    轍
    -0.92
    '
    -0.90
     overview
    -0.89
    POSITIVE LOGITS
     different
    1.48
    んですね
    1.20
    んですよね
    1.20
     few
    1.20
     two
    1.19
    dits
    1.17
    のですね
    1.14
     Vergnügen
    1.13
    んだろう
    1.12
     sentimenti
    1.12
    Activations Density 0.007%

    No Known Activations