© 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. 10-GEMMASCOPE-RES-131K
    7. 12081
    Prev
    Next
    INDEX
    Explanations

    wax or peng

    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
    The
    -3.39
    ༀ
    -2.84
    應該
    -2.83
    ين
    -2.75
    .”
    -2.48
     vollständige
    -2.48
     verbess
    -2.41
    
    -2.38
    ...");
    -2.38
    骉
    -2.36
    POSITIVE LOGITS
     has
    2.63
    s
    2.39
     we
    2.33
     be
    2.30
     eternally
    2.00
    y
    1.96
     heisst
    1.92
     endlessly
    1.91
     Werken
    1.90
     главный
    1.88
    Activations Density 0.003%

    No Known Activations