© 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. 34-GEMMASCOPE-RES-131K
    7. 49979
    Prev
    Next
    INDEX
    Explanations

    justice followed by name

    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
    particles
    -0.94
    粒子
    -0.86
    чество
    -0.82
     Consul
    -0.82
     Hamas
    -0.82
    setupUi
    -0.82
    Particles
    -0.78
     المؤلف
    -0.77
    세요
    -0.75
     methanol
    -0.75
    POSITIVE LOGITS
     Supreme
    2.14
     justices
    1.94
     Justices
    1.92
    Supreme
    1.84
     Justice
    1.84
     Scal
    1.67
    Justice
    1.60
    Scal
    1.54
     SCOT
    1.46
     Gins
    1.38
    Activations Density 0.265%

    No Known Activations