© 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. 22-GEMMASCOPE-RES-131K
    7. 25738
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     
    -1.14
    ване
    -0.99
     formando
    -0.97
    жина
    -0.90
     by
    -0.90
    随时
    -0.90
     bater
    -0.88
     efic
    -0.88
     PROBLEMS
    -0.86
    eficiente
    -0.86
    POSITIVE LOGITS
     neues
    1.20
     Ответить
    1.20
    ′,
    1.16
     nuevas
    1.13
     istot
    1.13
    LÄ
    1.12
    ("/",
    1.11
    tives
    1.09
    />";
    1.09
    CurtirCurtir
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.