© 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. 10-GEMMASCOPE-RES-131K
    4. 11684
    Prev
    Next
    INDEX
    Explanations

    but introducing contrast

    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
    囖
    -1.74
     però
    -1.54
     البته
    -1.52
    
    -1.52
     sué
    -1.51
     mulig
    -1.48
     speelt
    -1.44
    Serviço
    -1.44
     ſome
    -1.42
     Vám
    -1.41
    POSITIVE LOGITS
     this
    1.99
     your
    1.62
     its
    1.57
     it
    1.55
    upakan
    1.41
     معه
    1.41
     his
    1.41
     about
    1.39
     because
    1.39
     during
    1.34
    Activations Density 0.023%

    No Known Activations