© 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. 8261
    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
    休
    -0.93
    ُّ
    -0.90
    وله
    -0.87
    Obstacles
    -0.85
     européens
    -0.84
     لیتر
    -0.84
     Sorge
    -0.83
    競
    -0.82
    urcht
    -0.82
    ytale
    -0.82
    POSITIVE LOGITS
    rootDir
    0.96
     پلاست
    0.86
     habrían
    0.86
    ฺ
    0.85
     behe
    0.85
     calamity
    0.84
    ettür
    0.83
    都想
    0.83
    ć
    0.83
    珮
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.