© 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. 102294
    Prev
    Next
    INDEX
    Explanations

    University

    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
    鬭
    -2.91
    
    -2.86
    在我
    -2.83
    ꪹ
    -2.81
    良し
    -2.80
     souvent
    -2.77
    ꜆
    -2.67
    優しく
    -2.67
    栳
    -2.64
     malgré
    -2.56
    POSITIVE LOGITS
    .
    2.94
    :
    2.89
    趼
    2.86
    <i>
    2.72
    𖡼
    2.70
     ingenious
    2.67
    <em>
    2.61
    ༐
    2.58
    %
    2.58
    s
    2.58
    Activations Density 0.026%

    No Known Activations