© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13261
    Prev
    Next
    INDEX
    Explanations

    Zhong, Chung, Addo names

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

    The neuron strongly activates on Chinese personal name tokens (e.g. “Zhong,” “Hong,” “Chung”) in author or citation lists.

    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
    瑧
    -2.92
    ᝢ
    -2.81
    蛧
    -2.63
     venuto
    -2.58
    犄
    -2.48
     makeshift
    -2.47
     gewöhnlich
    -2.44
     voluminous
    -2.41
    𖡼
    -2.36
    dacia
    -2.34
    POSITIVE LOGITS
     apresenta
    2.72
     terá
    2.72
    謦
    2.67
    鵙
    2.63
     serão
    2.55
    鹀
    2.55
    襌
    2.50
    Ꮴ
    2.45
    莯
    2.44
    ate
    2.42
    Activations Density 0.001%

    No Known Activations