© 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. 34-GEMMASCOPE-RES-131K
    7. 38604
    Prev
    Next
    INDEX
    Explanations

    production quantities

    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
    Minha
    -0.87
     penutup
    -0.87
     getPrice
    -0.86
     ujar
    -0.85
     keamanan
    -0.84
    wahl
    -0.83
    Yap
    -0.83
     TTL
    -0.81
     Carefully
    -0.81
     hujan
    -0.81
    POSITIVE LOGITS
     production
    2.08
    production
    1.77
    Production
    1.52
     Production
    1.51
     manufacturing
    1.34
     PRODUCTION
    1.27
     productions
    1.26
     plant
    1.20
     produção
    1.20
     factory
    1.20
    Activations Density 0.019%

    No Known Activations