© 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. 34-GEMMASCOPE-RES-131K
    4. 110944
    Prev
    Next
    INDEX
    Explanations

    game 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
     visual
    -1.13
    visual
    -1.04
     Visual
    -0.91
     визу
    -0.87
    Visual
    -0.84
     visually
    -0.84
     VISUAL
    -0.83
    zbęd
    -0.80
    VISUAL
    -0.79
    innan
    -0.77
    POSITIVE LOGITS
     design
    2.44
     designer
    2.13
    design
    2.08
    DESIGN
    2.03
     Design
    2.02
     diseño
    2.02
    Design
    1.99
     designers
    1.95
     DESIGN
    1.95
    Designer
    1.75
    Activations Density 0.047%

    No Known Activations