© 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. 34-GEMMASCOPE-RES-131K
    7. 12206
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     many
    -1.18
     some
    -1.16
     quickly
    -1.03
     quite
    -1.02
     dozens
    -1.00
     several
    -0.98
     any
    -0.98
     countless
    -0.96
     zaragoza
    -0.96
     extremo
    -0.95
    POSITIVE LOGITS
     ^{\
    1.11
     seleccionamos
    1.06
    NIH
    1.03
    wiście
    1.01
    asier
    1.01
    Aktuelle
    1.00
    Weiterlesen
    0.99
    êter
    0.98
    verständnis
    0.96
    Maß
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.