© 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. 75253
    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
     бампер
    -1.39
     اللاعب
    -1.21
    performing
    -1.18
     ۱۹
    -1.14
    contentPane
    -1.10
     Bakterien
    -1.09
    öll
    -1.09
    ÑOS
    -1.08
    ModelAdmin
    -1.08
    fla
    -1.07
    POSITIVE LOGITS
    Noter
    1.20
    replyreport
    1.14
    Limitation
    1.13
     because
    1.12
     utilizing
    1.09
    OOTDTY
    1.07
    Huhu
    1.05
    Neden
    1.05
    splitContainer
    1.04
     chré
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.