© 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. 11448
    Prev
    Next
    INDEX
    Explanations

    specialized words and entities

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

    This neuron responds to long, multi-syllable content words—especially specialized technical terms or proper names—that span multiple subword tokens.

    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
    臯
    -1.92
    🧌
    -1.77
    in
    -1.70
    1
    -1.68
    ruecos
    -1.59
    鹩
    -1.59
    if
    -1.57
     khoan
    -1.52
    コミュニ
    -1.50
    Ꮵ
    -1.49
    POSITIVE LOGITS
     Each
    1.98
    летка
    1.85
     Except
    1.72
     Among
    1.70
     Eventually
    1.63
     Unless
    1.63
    iconductors
    1.59
     mengangg
    1.55
    ilización
    1.55
    зви
    1.54
    Activations Density 0.025%

    No Known Activations