© 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. 10-GEMMASCOPE-RES-131K
    7. 112027
    Prev
    Next
    INDEX
    Explanations

    Russian religious leaders

    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_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
    泚
    -2.28
     vendar
    -2.05
    昻
    -1.95
     our
    -1.90
    
    -1.87
    𓄹
    -1.84
    What
    -1.84
    漚
    -1.81
    覩
    -1.80
    を起こ
    -1.73
    POSITIVE LOGITS
     但
    1.98
    乆
    1.98
     it
    1.88
    чал
    1.88
    ↵↵
    1.86
     in
    1.82
    Provence
    1.78
     vorigen
    1.78
    QPalette
    1.78
    镠
    1.77
    Activations Density 0.000%

    No Known Activations