© 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. 85283
    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
    らず
    -1.07
     gasto
    -1.04
     }],
    -1.00
    cension
    -0.99
     /\.(
    -0.93
     vody
    -0.91
     humain
    -0.90
    скій
    -0.89
    orp
    -0.89
    谈判
    -0.88
    POSITIVE LOGITS
     tenemos
    1.06
    шками
    1.02
     they
    1.01
     dortmund
    0.99
     entonces
    0.94
     entitled
    0.91
    iej
    0.90
    Abb
    0.90
     budapest
    0.89
    پور
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.