© 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. 70468
    Prev
    Next
    INDEX
    Explanations

    byzantine empire and associated terms

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

    The neuron fires on multi-syllable capitalized names—that is, it picks out proper nouns and named entities.

    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
    genodigd
    -2.13
     translates
    -2.09
    "
    -2.06
    辚
    -2.02
     mused
    -2.02
    -"
    -1.96
    鰾
    -1.94
    =
    -1.93
    饃
    -1.91
    の魅力
    -1.89
    POSITIVE LOGITS
     الاجتماعي
    2.03
    槳
    1.91
    硖
    1.89
    in
    1.87
    standes
    1.83
    鳙
    1.81
    uttori
    1.80
    窦
    1.80
    tischen
    1.77
     способ
    1.77
    Activations Density 0.003%

    No Known Activations