© 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. 84043
    Prev
    Next
    INDEX
    Explanations

    IT and client services

    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
     Sucre
    -0.74
    陌生
    -0.74
    igia
    -0.73
     Certificado
    -0.72
    蹲
    -0.71
    Nate
    -0.70
     教
    -0.70
     scraped
    -0.69
    スパイ
    -0.69
     przypad
    -0.68
    POSITIVE LOGITS
     IT
    1.00
     Client
    0.96
     Computer
    0.95
     TCS
    0.95
     Consulting
    0.94
     client
    0.92
     tennis
    0.91
     Infos
    0.90
    client
    0.89
    TCS
    0.87
    Activations Density 0.021%

    No Known Activations