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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 77
    Prev
    Next
    INDEX
    Explanations

    sound audio systems

    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
    Zas
    -0.82
    гел
    -0.81
    ंदर
    -0.79
    ğin
    -0.79
    ọng
    -0.75
    丹药
    -0.74
    γή
    -0.74
     щ
    -0.73
     misread
    -0.72
    cadre
    -0.71
    POSITIVE LOGITS
     system
    1.99
     audio
    1.67
     systems
    1.66
    システム
    1.48
    系统
    1.48
     sound
    1.41
    Audio
    1.41
     système
    1.38
    SYSTEM
    1.35
    system
    1.33
    Activations Density 0.030%

    No Known Activations