© 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. 84685
    Prev
    Next
    INDEX
    Explanations

    operator overloading and lazy properties

    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
    我們
    -1.71
     некоторых
    -1.70
    hline
    -1.66
    我们
    -1.66
    C
    -1.53
    我们的
    -1.41
    受欢迎
    -1.40
    R
    -1.40
    感觉
    -1.39
     некоторые
    -1.39
    POSITIVE LOGITS
    龊
    1.73
    >
    1.49
    ницей
    1.42
    
    1.41
     vanil
    1.37
     anún
    1.35
     rz
    1.34
     toate
    1.34
     特典
    1.33
    fanfic
    1.31
    Activations Density 0.007%

    No Known Activations