© 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. 48143
    Prev
    Next
    INDEX
    Explanations

    C# namespaces and code declarations

    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
    tôi
    -0.93
    ınızı
    -0.85
    Также
    -0.83
     recomendo
    -0.82
    Ὑ
    -0.76
    forcer
    -0.73
    alibaba
    -0.72
    tım
    -0.71
    ınıza
    -0.69
     dach
    -0.69
    POSITIVE LOGITS
     Console
    1.03
    EventArgs
    1.01
     class
    0.98
     delegate
    0.96
    Console
    0.94
    ")]
    
    0.94
    委托
    0.93
     LIN
    0.90
     console
    0.90
     jagged
    0.90
    Activations Density 0.022%

    No Known Activations