© 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. 10-GEMMASCOPE-RES-131K
    7. 9179
    Prev
    Next
    INDEX
    Explanations

    areas and features

    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
     in
    -1.92
     podían
    -1.60
     many
    -1.57
     demuestra
    -1.55
    Many
    -1.53
     wichtigsten
    -1.51
     then
    -1.49
     envía
    -1.48
     оружи
    -1.47
     réuss
    -1.46
    POSITIVE LOGITS
     dó
    1.83
     hè
    1.66
     dì
    1.65
     bè
    1.65
     is
    1.62
     blad
    1.55
     plantes
    1.52
     ló
    1.51
     accepte
    1.49
     handels
    1.48
    Activations Density 0.074%

    No Known Activations