© 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. 41421
    Prev
    Next
    INDEX
    Explanations

    facebook likes

    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
    Whenever
    -1.43
    .”.
    -1.41
    However
    -1.41
    m
    -1.38
     設計
    -1.38
     goin
    -1.37
     endgül
    -1.35
     Socialism
    -1.33
    !”
    -1.32
     takže
    -1.32
    POSITIVE LOGITS
    幛
    1.58
     увидел
    1.54
     caminhão
    1.48
     pudieron
    1.48
    埽
    1.45
     protagonistas
    1.39
     купить
    1.38
     puedo
    1.38
            
    1.38
     vetores
    1.38
    Activations Density 0.019%

    No Known Activations