© 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. 72652
    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
     rajut
    -2.73
    czego
    -2.45
     multicolore
    -2.36
     nyeri
    -2.33
     abiye
    -2.27
     sécher
    -2.27
     vendeur
    -2.25
     hırka
    -2.23
     menek
    -2.16
     PÅ
    -2.16
    POSITIVE LOGITS
     to
    2.95
    w
    2.52
     And
    2.50
     A
    2.47
    2.38
     D
    2.36
     In
    2.33
      
    2.31
     <
    2.31
     …
    2.30
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.