© 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. 22-GEMMASCOPE-RES-131K
    7. 128563
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    完成です
    -1.20
     ;
    -1.07
    
    -1.05
    好在
    -1.03
     mitään
    -1.03
    んご
    -1.02
     July
    -1.02
     have
    -1.02
     Wirkungen
    -1.01
     bezeichnen
    -1.00
    POSITIVE LOGITS
     بيها
    1.25
    岁的
    1.23
    Hilsen
    1.18
     igång
    1.17
     planten
    1.14
     kinderen
    1.13
    Élet
    1.12
    蹿
    1.10
     manier
    1.09
     grotte
    1.09
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.