© 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. 22-GEMMASCOPE-RES-131K
    7. 35667
    Prev
    Next
    INDEX
    Explanations

    Frontend, Server, password

    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_22/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
    的脸
    -1.16
     erinner
    -1.05
     maravill
    -1.05
     acogedor
    -1.03
     geprü
    -1.00
     recém
    -1.00
    
    -0.97
     señales
    -0.94
     cálido
    -0.92
     tornou
    -0.91
    POSITIVE LOGITS
    ΤΗ
    1.01
     from
    0.98
     .....
    0.93
     Würzburg
    0.93
     solely
    0.91
     或
    0.90
    😶
    0.88
     cento
    0.87
    各地
    0.86
     manajemen
    0.85
    Activations Density 0.074%

    No Known Activations