© 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. 60583
    Prev
    Next
    INDEX
    Explanations

    sports medals

    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
    。　　
    -3.14
    迓
    -2.84
    ⎚
    -2.55
    怍
    -2.55
    棐
    -2.50
    𝙖
    -2.48
    謄
    -2.45
    眼下
    -2.45
     RoutedEventArgs
    -2.42
    Skocz
    -2.41
    POSITIVE LOGITS
     
    2.98
    A
    2.73
    a
    2.70
    但
    2.70
    お腹
    2.48
    ↵
    2.44
    是啊
    2.36
    さっき
    2.33
    并且
    2.28
    筈
    2.27
    Activations Density 0.003%

    No Known Activations