© 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. 105095
    Prev
    Next
    INDEX
    Explanations

    old towns and cities

    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
    饪
    -1.77
    他知道
    -1.73
    </h3>
    -1.70
    2
    -1.69
    楽しみです
    -1.52
    6
    -1.50
    jà
    -1.50
    不就是
    -1.48
    好像是
    -1.45
     the
    -1.44
    POSITIVE LOGITS
     of
    1.99
    四川
    1.46
    :
    1.41
    这是一个
    1.39
    血糖
    1.38
    有一个
    1.35
    ↵
    1.33
    南京
    1.32
    人工智能
    1.32
    重庆
    1.31
    Activations Density 0.019%

    No Known Activations