© 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. 9459
    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
     for
    -2.05
     only
    -1.98
     more
    -1.88
     with
    -1.84
     from
    -1.81
     many
    -1.80
     their
    -1.77
     or
    -1.75
     most
    -1.69
     has
    -1.66
    POSITIVE LOGITS
    킁
    1.63
     ferocious
    1.55
    
    1.52
     gigantic
    1.48
     ส์
    1.48
     insanely
    1.41
     horrid
    1.38
     ridiculously
    1.38
     wondrous
    1.37
     ludicrous
    1.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.