© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71303
    Prev
    Next
    INDEX
    Explanations

    words beginning with Qu

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

    The neuron fires whenever it sees the two‐letter sequence “Qu” as its own token (e.g. the “Qu” in Quanzhou, Quinte, etc.).

    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
    s
    -3.13
    ſſel
    -3.05
    ్వ
    -2.91
     moglie
    -2.80
    蹋
    -2.75
    すすめ
    -2.66
    圌
    -2.63
    埸
    -2.61
    鲧
    -2.55
    wiście
    -2.52
    POSITIVE LOGITS
    0
    3.38
     
    3.22
    ing
    2.95
     &
    2.92
     Quando
    2.86
    ～～
    2.78
    2
    2.70
    くらいの
    2.69
    だけではなく
    2.64
    だけでなく
    2.56
    Activations Density 0.002%

    No Known Activations