© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93343
    Prev
    Next
    INDEX
    Explanations

    mathematical specification and complexity

    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
     étui
    -1.34
     FINANCIAL
    -1.28
     туристи
    -1.26
     MUSEUM
    -1.24
    ַּ
    -1.24
     dégustation
    -1.22
     BROS
    -1.20
    
    -1.20
     chansons
    -1.20
    ְּ
    -1.20
    POSITIVE LOGITS
     systems
    1.57
     we
    1.50
     models
    1.45
     tools
    1.44
     methods
    1.39
     solutions
    1.35
     \
    1.34
     studies
    1.33
     diseñ
    1.32
     Unterricht
    1.32
    Activations Density 0.157%

    No Known Activations