© 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. 99497
    Prev
    Next
    INDEX
    Explanations

    measurement devices

    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
     paille
    -1.60
     habile
    -1.52
     corriger
    -1.52
    這
    -1.52
    んだから
    -1.45
     szary
    -1.44
     šed
    -1.44
     diſt
    -1.42
     déchir
    -1.42
     Livraison
    -1.41
    POSITIVE LOGITS
     on
    2.02
     in
    1.91
     both
    1.68
     over
    1.63
     all
    1.61
     Both
    1.45
     through
    1.38
     has
    1.33
     would
    1.30
     either
    1.30
    Activations Density 3.593%

    No Known Activations