© 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. 34-GEMMASCOPE-RES-131K
    7. 103119
    Prev
    Next
    INDEX
    Explanations

    functional programming and monads

    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_34/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
    gemeente
    -0.78
    اره
    -0.73
    usalem
    -0.71
    
    -0.71
    rug
    -0.71
    LineWidth
    -0.71
     decarbon
    -0.70
    mbggenerated
    -0.70
    corpus
    -0.69
    ísticas
    -0.68
    POSITIVE LOGITS
     functional
    1.10
    functional
    1.05
     Functional
    1.05
     Higher
    0.99
     lenses
    0.97
    Functional
    0.97
    Curry
    0.95
    licative
    0.94
    Lens
    0.94
     Haskell
    0.93
    Activations Density 0.136%

    No Known Activations