© 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. 71565
    Prev
    Next
    INDEX
    Explanations

    pairs and groupings

    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
     then
    -0.98
    rativo
    -0.94
     that
    -0.86
    pdev
    -0.86
     réessayer
    -0.84
     focused
    -0.84
     comédie
    -0.82
     response
    -0.81
     methods
    -0.81
     cheerful
    -0.81
    POSITIVE LOGITS
    Pairs
    1.01
     pairs
    0.93
     pairings
    0.86
     GENERATED
    0.84
    ñan
    0.83
     kleinere
    0.82
     egyszerű
    0.82
    provide
    0.82
    Listen
    0.80
    лети
    0.80
    Activations Density 0.010%

    No Known Activations