© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128485
    Prev
    Next
    INDEX
    Explanations

    umbrella and related organizations

    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
    他的
    -3.16
    在我
    -2.80
    訁
    -2.78
    
    -2.53
    狨
    -2.48
    翃
    -2.48
    她
    -2.45
    矬
    -2.44
    在我的
    -2.39
     लेकिन
    -2.36
    POSITIVE LOGITS
    鈇
    2.42
    这一次
    2.42
    趼
    2.39
    ,”
    2.31
     includes
    2.30
    U
    2.28
     focussing
    2.27
     of
    2.27
    )”
    2.25
    𓆜
    2.23
    Activations Density 0.004%

    No Known Activations