© 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. 99359
    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
    шом
    -0.94
     placés
    -0.91
    änge
    -0.88
     すぎ
    -0.86
     allude
    -0.85
    λι
    -0.84
     identifiés
    -0.84
     didnt
    -0.84
     всего
    -0.82
    怎么回事
    -0.81
    POSITIVE LOGITS
    鲽
    0.93
    (!__
    0.91
    Perform
    0.90
    vať
    0.88
    Kor
    0.87
     Архиви
    0.85
     CANCEL
    0.81
     chiesto
    0.81
    edere
    0.81
     '../../../../
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.