© 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. 70986
    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
     if
    -1.76
     before
    -1.55
     during
    -1.53
     just
    -1.43
     sopa
    -1.37
     after
    -1.36
     from
    -1.34
     intricacies
    -1.34
    :%.
    -1.25
     biber
    -1.23
    POSITIVE LOGITS
     stück
    1.45
     marvelous
    1.39
     horrid
    1.38
     stalwart
    1.35
     insanely
    1.35
     dreadful
    1.30
     nyní
    1.29
     takich
    1.28
     myriad
    1.28
     現在
    1.27
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.