© 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. 85213
    Prev
    Next
    INDEX
    Explanations

    Netherlands

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

    The neuron fires specifically on occurrences of the country name “Netherlands.”

    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
     faldas
    -2.02
     pintados
    -1.99
    뻗
    -1.96
     they
    -1.91
    邂
    -1.90
    咘
    -1.84
     falsas
    -1.81
     咖啡
    -1.80
    neurial
    -1.75
     资源
    -1.75
    POSITIVE LOGITS
    ↵
    2.61
    翾
    2.23
    ],
    1.94
    殽
    1.88
     Wahrnehmung
    1.87
     Referring
    1.84
    的主要
    1.84
     贈
    1.81
     serão
    1.80
     custa
    1.78
    Activations Density 0.006%

    No Known Activations