Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8749
    Prev
    Next
    INDEX
    Explanations

    cloud computing technologies

    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
     Tablet
    -0.77
    фикация
    -0.74
     Beer
    -0.72
    Page
    -0.71
     siehe
    -0.69
     hvid
    -0.69
     junior
    -0.68
     저장
    -0.68
    engelsk
    -0.67
     солне
    -0.67
    POSITIVE LOGITS
     private
    0.91
     hybrid
    0.88
    Consumption
    0.83
    tahui
    0.82
    consumption
    0.81
     opérateur
    0.77
    ıllı
    0.77
     consumption
    0.77
     Kubernetes
    0.77
     montant
    0.76
    Activations Density 0.019%

    No Known Activations