© 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. 127935
    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
    1
    -1.21
    ненный
    -1.07
     coelho
    -1.01
    hlás
    -0.99
    levé
    -0.96
     we
    -0.94
    其妙
    -0.94
    ⠊
    -0.92
     potes
    -0.91
    های
    -0.91
    POSITIVE LOGITS
     mehrere
    1.22
    RIST
    1.09
     overlaid
    1.03
    灩
    1.02
    ясь
    1.01
    这是什么
    1.01
    туру
    1.00
     enfrent
    0.99
    隙間
    0.99
    様々
    0.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.