© 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. 69944
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    就是
    -3.33
    就
    -3.27
    .”
    -3.19
    也
    -3.13
    或者
    -3.09
    是
    -2.81
    有
    -2.70
    或
    -2.63
    才
    -2.59
    对
    -2.52
    POSITIVE LOGITS
    .
    3.66
    鹛
    2.97
    蚡
    2.73
    ᠁
    2.70
    罴
    2.69
    绝望
    2.59
    
    2.56
    鈈
    2.44
    柃
    2.42
    鹀
    2.39
    Activations Density 0.005%

    No Known Activations