© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75378
    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
     get
    -1.15
     came
    -1.12
     should
    -1.09
     with
    -1.09
     take
    -1.08
     all
    -1.03
     allow
    -1.03
     usually
    -1.02
     three
    -1.02
     have
    -1.02
    POSITIVE LOGITS
     continuer
    1.27
     ats
    1.19
     ADDITIONAL
    1.16
     ies
    1.13
    Welche
    1.11
    
    1.09
    Aantal
    1.09
     emplo
    1.08
    Diese
    1.06
     INSPIRE
    1.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.