© 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. 105879
    Prev
    Next
    INDEX
    Explanations

    dates of events

    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
    ],
    -1.94
    咴
    -1.91
    现有
    -1.91
    "},
    -1.88
    ),
    -1.87
     позволит
    -1.77
    ).
    -1.75
    体は
    -1.74
    ,"
    -1.73
    
    -1.71
    POSITIVE LOGITS
    2
    2.11
     spannende
    1.90
    l
    1.89
    iſter
    1.88
    ↵
    1.88
     respostas
    1.87
    法國
    1.77
     selepas
    1.76
     besondere
    1.68
    ꜆
    1.66
    Activations Density 0.013%

    No Known Activations