© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68529
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and accountability

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

    The neuron detects mentions of legal proceedings and courtroom actions (e.g., trials, charges, and bringing someone to justice).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     adhesivo
    -1.41
     alimentaria
    -1.40
     neumáticos
    -1.40
     soldadura
    -1.32
    _
    -1.31
     cuarent
    -1.28
     sellado
    -1.28
     acogedor
    -1.27
     dinámico
    -1.27
     bricolaje
    -1.27
    POSITIVE LOGITS
     for
    2.23
     what
    1.67
     However
    1.34
    砹
    1.32
    mallows
    1.32
     With
    1.24
    ？』
    1.24
     Since
    1.23
    柚
    1.23
    友人
    1.21
    Activations Density 0.035%

    No Known Activations