© 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. 35739
    Prev
    Next
    INDEX
    Explanations

    live sports coverage and broadcasts

    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
     work
    -1.38
     problems
    -1.31
     maintain
    -1.23
     gently
    -1.19
     new
    -1.18
     cuya
    -1.18
     creating
    -1.13
     about
    -1.12
     medical
    -1.12
     water
    -1.11
    POSITIVE LOGITS
     coverage
    1.65
     terrasse
    1.62
     poë
    1.54
     COVERAGE
    1.52
     assister
    1.46
     milliard
    1.44
     FALLS
    1.42
     siè
    1.41
     brille
    1.38
     appartement
    1.34
    Activations Density 0.033%

    No Known Activations