© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106587
    Prev
    Next
    INDEX
    Explanations

    ruled that

    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
     CRITICAL
    -0.76
     MISSION
    -0.75
    行政
    -0.74
     bildet
    -0.73
     PRACTICAL
    -0.71
    üks
    -0.70
    ជ
    -0.69
    ssaint
    -0.67
     MACRO
    -0.67
     algumas
    -0.66
    POSITIVE LOGITS
     ruled
    1.24
     ruling
    1.21
     rule
    1.12
     Chair
    1.11
     rulings
    1.03
    ruled
    1.01
     disciplined
    0.98
     Disorder
    0.94
     Rules
    0.94
     rules
    0.92
    Activations Density 0.021%

    No Known Activations