© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116482
    Prev
    Next
    INDEX
    Explanations

    Champions League and cups

    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
    vagrant
    -1.00
    cultures
    -0.89
    θε
    -0.84
     外観
    -0.84
    kimono
    -0.84
    sneaker
    -0.82
     condam
    -0.80
     duce
    -0.79
     Chinese
    -0.79
    thren
    -0.79
    POSITIVE LOGITS
     League
    1.94
     league
    1.54
    League
    1.48
    league
    1.16
     Leagues
    0.97
     leagues
    0.94
     LEAGUE
    0.87
     Spotify
    0.84
     Guild
    0.82
    Liga
    0.81
    Activations Density 0.013%

    No Known Activations