© 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. 70945
    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
     to
    -1.58
     when
    -1.53
     if
    -1.41
     after
    -1.41
     so
    -1.23
     this
    -1.23
     dager
    -1.17
     for
    -1.15
     that
    -1.12
     januari
    -1.09
    POSITIVE LOGITS
     trám
    1.28
     opulent
    1.20
    なかな
    1.19
    割と
    1.18
    あっという
    1.18
     amazingly
    1.17
     AMAZING
    1.16
     boister
    1.15
     streamlining
    1.13
     marvelous
    1.13
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.