© 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. 20298
    Prev
    Next
    INDEX
    Explanations

    defendant contends

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

    The neuron flags the word “Defendant” (and related defendant–appellant labels) in legal case documents.

    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
    </h4>
    -2.58
     antaranya
    -2.42
    liegenden
    -2.30
     `
    -2.14
     répondu
    -2.13
    or
    -2.13
    ⧠
    -2.11
    </strong>
    -2.09
    Proteins
    -2.08
     leurs
    -2.06
    POSITIVE LOGITS
    淠
    3.28
    岨
    2.86
    饃
    2.67
    鯔
    2.53
    投稿日
    2.50
    ♪♪
    2.50
    泐
    2.44
     プレミアム
    2.42
    훙
    2.41
    Ꮉ
    2.41
    Activations Density 0.020%

    No Known Activations