© 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. 90341
    Prev
    Next
    INDEX
    Explanations

    cans of

    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
    鷽
    -1.93
    在他
    -1.91
    
    -1.73
    3
    -1.72
    ㊄
    -1.72
    if
    -1.67
     trebui
    -1.65
     that
    -1.65
    臯
    -1.63
    please
    -1.62
    POSITIVE LOGITS
     This
    1.97
    ˃
    1.96
     of
    1.88
    
    1.88
    IANGLES
    1.73
    Ⅳ
    1.65
    ＄
    1.64
     มัน
    1.56
    इटम
    1.55
    ممنون
    1.55
    Activations Density 0.020%

    No Known Activations