© 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. 11057
    Prev
    Next
    INDEX
    Explanations

    jury delivering a verdict

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

    The neuron activates on mentions of a jury (including “jury” or “jurors”) in the text.

    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
     leaſt
    -3.25
     durch
    -2.69
     เป็น
    -2.64
     Eigentü
    -2.64
     могут
    -2.61
    咴
    -2.56
    नलोड
    -2.56
    …。
    -2.52
     Gläub
    -2.52
    tividade
    -2.48
    POSITIVE LOGITS
    说不
    2.19
    方がいい
    2.13
    凇
    2.02
    ほうがいい
    2.02
    照顾
    2.02
    早めに
    2.00
     funcionam
    1.97
    ೣ
    1.96
     fechar
    1.96
     aqueles
    1.96
    Activations Density 0.003%

    No Known Activations