© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12379
    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
    子が
    -1.13
     recette
    -0.95
     frasco
    -0.95
     jokingly
    -0.93
     fourn
    -0.90
     that
    -0.90
     плану
    -0.89
    日が
    -0.89
     pâte
    -0.88
    朝鲜
    -0.88
    POSITIVE LOGITS
     Erinner
    1.26
    小さく
    1.00
    letoe
    0.98
    sique
    0.96
    enddo
    0.93
     unabhäng
    0.93
     kommenden
    0.93
     Empfehlungen
    0.91
     berühm
    0.90
     könnten
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.