© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104819
    Prev
    Next
    INDEX
    Explanations

    que type, que make, que when

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

    The neuron detects common Spanish/Portuguese question words (e.g. “que,” “qué,” “cómo,” “cuándo”).

    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
     schnellen
    -2.22
     geringen
    -2.02
     praktischen
    -1.89
     grito
    -1.88
     sicheren
    -1.77
    今月
    -1.75
     eléctrica
    -1.70
     speziellen
    -1.68
     Fassung
    -1.68
    nappropriate
    -1.67
    POSITIVE LOGITS
     unſ
    2.00
     The
    1.97
     unless
    1.88
     called
    1.77
     were
    1.76
    篁
    1.75
    kiksi
    1.72
    н
    1.70
    ohjel
    1.70
    ///</
    1.69
    Activations Density 0.001%

    No Known Activations