© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8817
    Prev
    Next
    INDEX
    Explanations

    World Cup qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite

    World Cup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     வேளாண்
    0.60
     రైతు
    0.60
    萜
    0.60
     थर्मल
    0.57
    陕
    0.55
     cropland
    0.54
    ሦ
    0.54
     zásobníku
    0.54
    毉
    0.54
    裒
    0.54
    POSITIVE LOGITS
     FIFA
    1.30
     Fifa
    1.16
     UEFA
    1.08
    FIFA
    1.04
     soccer
    0.99
     Soccer
    0.96
     futebol
    0.93
     Mundial
    0.92
     countries
    0.91
     Fußball
    0.89
    Activations Density 0.134%

    No Known Activations