© 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. 1353
    Prev
    Next
    INDEX
    Explanations

    Latin America

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

    The main thing this neuron does is detect references to “Latin America.”

    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
    睃
    -2.66
    麈
    -2.55
    鸫
    -2.44
    medriver
    -2.41
    AddHtmlAttribute
    -2.38
    ?’
    -2.38
    珰
    -2.38
    澇
    -2.38
    鹋
    -2.28
    はは
    -2.27
    POSITIVE LOGITS
    and
    3.48
    A
    2.77
    وضوع
    2.75
     ERSITY
    2.64
    most
    2.48
    ский
    2.47
    槩
    2.38
    硨
    2.36
     intensively
    2.33
    彞
    2.30
    Activations Density 0.004%

    No Known Activations