© 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. 802
    Prev
    Next
    INDEX
    Explanations

    working correctly

    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
     énorme
    -0.99
    窶
    -0.95
    cai
    -0.93
     bardzo
    -0.88
     チップ
    -0.85
     professionnels
    -0.85
    цією
    -0.85
    
    -0.84
     stationnement
    -0.84
    шком
    -0.83
    POSITIVE LOGITS
     properly
    2.03
     correctly
    1.62
    properly
    1.45
     well
    1.41
     correctamente
    1.39
    正常
    1.38
     normal
    1.35
     нормально
    1.30
     proper
    1.27
     normally
    1.27
    Activations Density 0.099%

    No Known Activations