© 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. 34-GEMMASCOPE-RES-131K
    7. 92324
    Prev
    Next
    INDEX
    Explanations

    football leagues and divisions

    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_34/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
     Frankel
    -0.79
    ifflin
    -0.79
    squareup
    -0.77
    かける
    -0.77
    林
    -0.74
     nguoi
    -0.73
    حديث
    -0.72
     Ninth
    -0.70
    匐
    -0.70
     dependence
    -0.69
    POSITIVE LOGITS
     overrated
    0.75
    umani
    0.73
     sightings
    0.73
    眠
    0.72
     Nore
    0.71
    ILLA
    0.70
    ionate
    0.69
    entia
    0.68
    ENTE
    0.68
     McDonald
    0.67
    Activations Density 0.035%

    No Known Activations