© 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. 104450
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and domains

    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
     mouvements
    -1.09
     Guille
    -1.08
    也非常
    -0.96
     VILL
    -0.95
    δυ
    -0.93
     هفته
    -0.92
     papiers
    -0.90
    ęty
    -0.88
     Cristi
    -0.88
     源
    -0.87
    POSITIVE LOGITS
     his
    1.20
     their
    1.05
     protože
    0.97
    ffindor
    0.95
     then
    0.93
    ują
    0.93
    teten
    0.93
    Tämä
    0.93
    судар
    0.92
     jego
    0.92
    Activations Density 0.050%

    No Known Activations