© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65282
    Prev
    Next
    INDEX
    Explanations

    US Supreme Court and judges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     teclado
    -0.95
     Negotiations
    -0.94
    ópolis
    -0.91
     GERMANY
    -0.90
    issantes
    -0.88
     batterie
    -0.88
     Dutt
    -0.88
     accus
    -0.88
    .«
    -0.87
     recomendación
    -0.87
    POSITIVE LOGITS
     Supreme
    2.09
    Supreme
    1.64
     Justices
    1.53
     justices
    1.36
     SCOT
    1.33
     judges
    1.30
     constitutional
    1.22
     Court
    1.20
     Верхов
    1.20
     Judges
    1.13
    Activations Density 0.050%

    No Known Activations