© 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. 98380
    Prev
    Next
    INDEX
    Explanations

    Serbian language, people, and places

    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
    Gand
    -0.83
    Kau
    -0.79
    Namibia
    -0.79
     हमारा
    -0.78
    configs
    -0.77
     Dein
    -0.76
     निम्
    -0.74
    ờ
    -0.74
     Quo
    -0.73
    第一天
    -0.73
    POSITIVE LOGITS
     Serbian
    1.66
     Serbia
    1.48
     Belgrade
    1.22
    Serbia
    1.19
     Djokovic
    1.10
     Serbie
    0.93
     Aleks
    0.88
     Jovan
    0.87
     Dj
    0.85
     ____
    0.85
    Activations Density 0.050%

    No Known Activations