© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9293
    Prev
    Next
    INDEX
    Explanations

    championships and youth tournaments

    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_10/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
     visse
    -1.44
    ciąg
    -1.36
     garantis
    -1.31
     meub
    -1.24
     épaules
    -1.23
     lâng
    -1.23
     interieur
    -1.23
    洐
    -1.22
     éta
    -1.22
     unul
    -1.18
    POSITIVE LOGITS
     all
    1.95
    TEntity
    1.33
     even
    1.23
     Jeden
    1.19
     from
    1.19
     всех
    1.16
    "
    
    1.14
     would
    1.13
    withId
    1.12
    ThemeProvider
    1.09
    Activations Density 0.117%

    No Known Activations