© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110571
    Prev
    Next
    INDEX
    Explanations

    legal case respondent

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

    The neuron detects legal party role labels (e.g. “Appellant,” “Respondent,” “Petitioner”) in case captions.

    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
    趿
    -1.91
     sayfa
    -1.87
     we
    -1.85
     efficacité
    -1.84
    ConfigureAwait
    -1.81
     geldi
    -1.80
    z
    -1.77
    jelaskan
    -1.73
    RTLU
    -1.73
    Kapitel
    -1.70
    POSITIVE LOGITS
    2.39
    That
    2.38
    ].
    2.05
    B
    1.94
    At
    1.93
    While
    1.88
    \
    1.88
     Möglichkeit
    1.86
    <strong>
    1.85
    ).
    1.80
    Activations Density 0.061%

    No Known Activations