© 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. 102224
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and judgments

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

    The neuron detects mentions of courts, judges, and formal legal decision headings.

    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
    requipa
    -1.31
     publier
    -1.29
     leurs
    -1.26
     angele
    -1.25
    weile
    -1.14
     Nacho
    -1.14
     gede
    -1.14
     contrôler
    -1.14
     Majefty
    -1.13
     nadal
    -1.10
    POSITIVE LOGITS
    )>>
    1.24
     with
    1.22
     willing
    1.17
    京城
    1.14
     about
    1.11
     directly
    1.09
    élica
    1.09
    水墨
    1.06
     saber
    1.06
     using
    1.06
    Activations Density 0.103%

    No Known Activations