© 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. 10-GEMMASCOPE-RES-131K
    7. 86789
    Prev
    Next
    INDEX
    Explanations

    articles and stories

    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_10/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
    ),
    -2.75
     you
    -2.11
    讴
    -1.92
    ранее
    -1.89
     However
    -1.71
    他也
    -1.70
    uschen
    -1.67
    ďaka
    -1.66
     zahlreiche
    -1.62
    iguity
    -1.61
    POSITIVE LOGITS
    ܊
    2.09
     összefoglaló
    2.02
     geheim
    1.95
     花纹
    1.95
    :
    1.94
    
    1.91
    ዣ
    1.91
    栳
    1.90
    觏
    1.85
     сожа
    1.84
    Activations Density 0.003%

    No Known Activations