© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5417
    Prev
    Next
    INDEX
    Explanations

    sports team mascots

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

    sports teams

    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_53_width_65k_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
    ֮
    0.38
     personaje
    0.37
     औ
    0.37
    டுகிறது
    0.36
     contempla
    0.36
    像
    0.35
     ATPase
    0.35
    ׄ
    0.35
    בן
    0.35
    閏
    0.35
    POSITIVE LOGITS
     Panthers
    1.62
     Falcons
    1.62
     Bulldogs
    1.60
     Tigers
    1.58
     Broncos
    1.54
     Cougars
    1.52
     Cardinals
    1.48
     Eagles
    1.47
     Seahawks
    1.46
     Raiders
    1.44
    Activations Density 0.178%

    No Known Activations