© 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. 29008
    Prev
    Next
    INDEX
    Explanations

    l' followed by vowel or h

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

    The neuron detects occurrences of the elided French definite article “L’” (i.e. “L’”-prefixes in French names or titles).

    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
    Surprisingly
    -2.42
    ramientas
    -2.13
    After
    -2.11
    During
    -2.11
    Many
    -2.09
    時間
    -2.06
    Regardless
    -2.02
    Numerous
    -2.02
     Surprisingly
    -2.02
    Two
    -1.99
    POSITIVE LOGITS
    ’
    2.34
     '
    2.31
    ならではの
    2.11
     cinq
    2.02
    while
    1.91
     "
    1.87
     '"
    1.87
     enti
    1.85
     trois
    1.84
    的一些
    1.84
    Activations Density 0.003%

    No Known Activations