© 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. 8328
    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
    δες
    -0.99
     praising
    -0.94
    Américaine
    -0.90
     lightly
    -0.88
    老公
    -0.88
     Europeo
    -0.88
     jei
    -0.84
     battling
    -0.84
     directing
    -0.84
     ruined
    -0.84
    POSITIVE LOGITS
     également
    1.11
     Access
    0.94
     Act
    0.94
    同样
    0.93
    mbh
    0.92
    飛機
    0.90
     Battalion
    0.90
     것은
    0.88
    せっ
    0.88
     Science
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.