© 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. 99406
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    zys
    -1.00
     africaine
    -0.96
    bater
    -0.94
     africain
    -0.93
     romain
    -0.91
     ier
    -0.90
    ıştı
    -0.90
    هاز
    -0.90
     thème
    -0.90
    זי
    -0.89
    POSITIVE LOGITS
    brtc
    1.25
    譴
    0.91
     également
    0.91
    說道
    0.91
     wealth
    0.88
    sions
    0.87
    揀
    0.86
    勸
    0.85
    hemiah
    0.85
    割と
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.