© 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. 22-GEMMASCOPE-RES-131K
    7. 70882
    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
     DEVELOPMENT
    -1.13
     irmã
    -1.08
     garota
    -1.06
    τικό
    -1.05
     FontFamily
    -1.05
    medriver
    -1.04
     escritora
    -1.03
    ẢN
    -1.02
    YMS
    -1.02
     autonome
    -1.00
    POSITIVE LOGITS
     return
    1.69
    return
    1.60
     Return
    1.15
     returning
    1.11
    .
    1.10
     OLIVER
    1.08
    </em>
    1.06
     najczęściej
    1.04
     húmedo
    1.03
     powietrza
    1.02
    Activations Density 0.001%

    No Known Activations