© 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. 65374
    Prev
    Next
    INDEX
    Explanations

    while clauses

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

    The neuron strongly activates on the subordinating conjunction “while.”

    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
     more
    -1.73
     somewhat
    -1.69
    Après
    -1.56
     further
    -1.54
     another
    -1.52
    𓐍
    -1.48
    Это
    -1.44
     tempio
    -1.43
     icona
    -1.41
    Ме
    -1.39
    POSITIVE LOGITS
     manteniendo
    1.55
     samochodu
    1.52
     while
    1.52
    .」
    1.50
     mientras
    1.48
     when
    1.47
     estando
    1.45
    大好きです
    1.42
     ofreciendo
    1.42
    常に
    1.41
    Activations Density 0.011%

    No Known Activations