© 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. 37913
    Prev
    Next
    INDEX
    Explanations

    list transformations

    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
     gastron
    -0.82
     deviennent
    -0.80
     chut
    -0.78
     labd
    -0.75
     conster
    -0.74
    velmente
    -0.73
    Enumerable
    -0.72
     caractéristique
    -0.72
     telev
    -0.71
    ✨✨
    -0.71
    POSITIVE LOGITS
    filter
    1.01
     filter
    1.00
    peek
    0.91
     peek
    0.87
    limit
    0.86
    sequential
    0.84
    findFirst
    0.80
     compared
    0.79
    map
    0.79
    collect
    0.78
    Activations Density 0.001%

    No Known Activations