© 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. 84766
    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
     Nevertheless
    -1.00
     Valdés
    -0.92
     Fútbol
    -0.87
     with
    -0.87
     Consequently
    -0.86
     Martí
    -0.85
    likopter
    -0.85
    ↵
    -0.84
    ]^{
    -0.84
     immorality
    -0.83
    POSITIVE LOGITS
     vux
    1.14
    쩡
    1.02
    这点
    1.02
    eniem
    0.96
    邻居
    0.94
    Olivia
    0.94
    instal
    0.94
     necesitas
    0.94
    kệ
    0.91
    Ө
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.