© 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. 130838
    Prev
    Next
    INDEX
    Explanations

    Hungarian context and names

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

    The neuron selectively activates on Hungarian words or morphemes—especially those containing accented characters.

    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
    ↵
    -2.14
     This
    -1.81
    '
    -1.76
    ’
    -1.72
     from
    -1.72
     in
    -1.63
     så
    -1.52
     of
    -1.49
     这
    -1.42
    osgi
    -1.41
    POSITIVE LOGITS
    cipais
    1.89
    あぁ
    1.77
    ではでは
    1.77
    ではまた
    1.68
     チラ
    1.63
    庒
    1.59
     ヌード
    1.57
    饜
    1.57
     palav
    1.55
     レスト
    1.55
    Activations Density 0.005%

    No Known Activations