© 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. 22-GEMMASCOPE-RES-131K
    7. 98350
    Prev
    Next
    INDEX
    Explanations

    goods and 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_22/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
    guigu
    -1.07
     abbildung
    -1.01
     manuale
    -0.98
    Достоинства
    -0.95
     paradiso
    -0.91
     damal
    -0.90
    łe
    -0.88
     daqui
    -0.85
    Роман
    -0.84
     variaciones
    -0.84
    POSITIVE LOGITS
     its
    1.55
     partnerships
    1.11
     capability
    1.09
     capabilities
    1.08
    вать
    1.02
    otex
    1.02
    ер
    1.02
     market
    1.01
     addSubview
    0.99
     partner
    0.98
    Activations Density 0.067%

    No Known Activations