© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129027
    Prev
    Next
    INDEX
    Explanations

    sports statistics

    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
     which
    -1.16
     because
    -1.14
     would
    -1.09
     without
    -1.02
     with
    -1.01
     their
    -1.00
     whose
    -0.98
     between
    -0.93
     using
    -0.93
     even
    -0.90
    POSITIVE LOGITS
     célè
    1.07
     mediocre
    0.98
     protéger
    0.94
    afp
    0.93
     marquer
    0.93
     المعيار
    0.89
     remplacer
    0.87
     déchir
    0.87
     vivent
    0.85
     développer
    0.85
    Activations Density 0.035%

    No Known Activations