© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65075
    Prev
    Next
    INDEX
    Explanations

    des followed by a noun

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

    The neuron primarily detects the French plural article “des.”

    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
     
    -2.67
    ⤦
    -2.48
     '"
    -2.34
     '
    -2.34
     "'
    -2.17
    穑
    -2.17
    ..........
    -2.16
     "
    -2.16
    ""
    -2.11
    臜
    -2.09
    POSITIVE LOGITS
    te
    2.95
    m
    2.88
    r
    2.53
    k
    2.50
    s
    2.34
    a
    2.30
     міся
    2.28
     punti
    2.27
     miliar
    2.25
    ’，
    2.22
    Activations Density 0.003%

    No Known Activations