© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130044
    Prev
    Next
    INDEX
    Explanations

    objective-c, javascript, c#, c++

    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
    蛩
    -2.97
    鼉
    -2.84
    诶
    -2.63
    ation
    -2.56
    这件事
    -2.52
    这件事情
    -2.50
    龔
    -2.47
    ⩥
    -2.42
    鯪
    -2.36
    鵙
    -2.33
    POSITIVE LOGITS
    '
    2.55
    ↵↵
    2.36
    籏
    2.25
    一秒
    2.17
    >
    2.17
     ก็
    2.16
     размеров
    2.14
    д
    2.09
     (‘
    2.05
    最重要
    2.02
    Activations Density 0.002%

    No Known Activations