© 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. 39256
    Prev
    Next
    INDEX
    Explanations

    Yuri, Goldberg, Weiss, Kuro, Thierry

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

    The neuron selectively activates on occurrences of the proper name “Yuri.”

    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
    I
    -3.48
    t
    -2.84
    ),
    -2.83
    "
    -2.80
     Would
    -2.70
    .,
    -2.63
    翃
    -2.61
    ".
    -2.59
     упаковка
    -2.55
     Commonly
    -2.48
    POSITIVE LOGITS
    
    2.88
    ︲
    2.72
    槼
    2.69
    呖
    2.63
    ⃚
    2.59
     analisis
    2.52
    銲
    2.52
    鰱
    2.50
    ၜ
    2.47
     territ
    2.44
    Activations Density 0.003%

    No Known Activations