© 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. 76104
    Prev
    Next
    INDEX
    Explanations

    architecture and design

    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
    roix
    -1.05
     LIVES
    -0.95
     musikal
    -0.91
     Calcio
    -0.91
    cucina
    -0.91
     hôtes
    -0.90
     kumar
    -0.89
     Azi
    -0.88
     PEAK
    -0.88
    "?>
    -0.88
    POSITIVE LOGITS
     architects
    2.92
     architectural
    2.84
     Architects
    2.52
     architect
    2.52
     architecture
    2.50
     design
    2.47
     Architecture
    2.47
     Architectural
    2.39
     designers
    2.34
     архитек
    2.22
    Activations Density 0.106%

    No Known Activations