© 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. 102355
    Prev
    Next
    INDEX
    Explanations

    modern sleek minimalist contemporary

    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
     nécessite
    -0.94
    explode
    -0.88
    ộm
    -0.87
    actéristique
    -0.84
    spania
    -0.82
    ｠
    -0.82
     раскра
    -0.82
    IZACIÓN
    -0.80
     ライブ
    -0.80
     deforma
    -0.80
    POSITIVE LOGITS
     modern
    2.78
     sleek
    2.67
     clean
    2.59
     minimalist
    2.28
     Modern
    2.17
     contemporary
    2.09
    Modern
    2.08
    modern
    2.05
     moderne
    1.98
     Clean
    1.88
    Activations Density 0.054%

    No Known Activations