© 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. 59677
    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
     pendientes
    -1.02
     düşünü
    -0.97
    cipline
    -0.93
     pendiente
    -0.93
    icare
    -0.93
     gier
    -0.89
    KELEY
    -0.89
     incluyendo
    -0.88
     detract
    -0.88
    SHARE
    -0.87
    POSITIVE LOGITS
     */
    0.97
     Those
    0.93
     расположен
    0.91
     обслуживание
    0.87
    古屋
    0.85
     Former
    0.84
    ],
    0.84
    ῖς
    0.82
     */
    0.82
    }
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.