© 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. 35888
    Prev
    Next
    INDEX
    Explanations

    products and industry suppliers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    licopter
    -1.56
    alers
    -1.50
     semillas
    -1.44
     variaciones
    -1.42
    iress
    -1.38
    eded
    -1.38
     Bewohner
    -1.35
     jiné
    -1.34
    athed
    -1.33
     people
    -1.31
    POSITIVE LOGITS
    靱
    1.70
    靭
    1.65
     product
    1.54
    歟
    1.46
     citroen
    1.44
     metus
    1.43
     geel
    1.41
     groen
    1.41
     products
    1.41
     acrylique
    1.38
    Activations Density 0.092%

    No Known Activations