© 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. 79667
    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
     hardly
    -1.16
     obvious
    -1.15
     albeit
    -1.13
     predominantly
    -1.12
     tremendous
    -1.11
     continually
    -1.11
     surely
    -1.09
     conster
    -1.07
     pesso
    -1.06
     powerfully
    -1.05
    POSITIVE LOGITS
     memahami
    1.24
    kmäler
    1.21
    1.20
     kekinian
    1.18
     során
    1.16
     wisatawan
    1.13
     vinaigre
    1.13
     paham
    1.11
    多かった
    1.11
     ratusan
    1.11
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.