© 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. 110653
    Prev
    Next
    INDEX
    Explanations

    Queen followed by names

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

    The neuron responds to occurrences of the title or name “Queen.”

    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
     in
    -2.75
     egregious
    -2.70
    งิน
    -2.47
    轳
    -2.28
     bekannten
    -2.23
     दोनों
    -2.17
    ?"
    -2.14
    giaan
    -2.14
     \%$
    -2.13
     ที่
    -2.13
    POSITIVE LOGITS
    E
    2.73
    蟊
    2.72
     russo
    2.61
     تنظ
    2.56
     baumwolle
    2.42
     хотела
    2.30
    X
    2.30
     essais
    2.27
     bianca
    2.25
     QUEEN
    2.25
    Activations Density 0.004%

    No Known Activations