© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11021
    Prev
    Next
    INDEX
    Explanations

    sports and athletes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    উন্ট
    1.39
     Enlightenment
    1.36
     Pond
    1.35
     solids
    1.35
     resistivity
    1.34
    quire
    1.34
     brush
    1.32
    駕
    1.30
     artisans
    1.30
     Solids
    1.30
    POSITIVE LOGITS
     voetbal
    2.55
    試合
    2.46
     futebol
    2.44
    球迷
    2.42
    กีฬา
    2.42
    运动员
    2.40
     футбо
    2.39
    sports
    2.39
     Stadion
    2.35
    soccer
    2.33
    Activations Density 0.942%

    No Known Activations