© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 33562
    Prev
    Next
    INDEX
    Explanations

    conversion and transformation

    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
    melten
    -1.04
     pasamos
    -1.01
    ために
    -0.94
     creemos
    -0.92
     коль
    -0.91
     متحده
    -0.91
     الأرض
    -0.91
    หรือ
    -0.89
    oc
    -0.88
    
    -0.88
    POSITIVE LOGITS
     Conversion
    2.81
     conversion
    2.47
    conversion
    2.20
     Converting
    2.08
    Conversion
    2.02
     Converter
    1.98
     Convert
    1.95
     Conversions
    1.95
     conversions
    1.94
     convert
    1.91
    Activations Density 0.034%

    No Known Activations