© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5855
    Prev
    Next
    INDEX
    Explanations

    referee actions and decisions

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

    officiating game rules

    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
     прогноз
    0.41
    itekt
    0.40
     жет
    0.40
     බැ
    0.39
    伈
    0.39
     乗
    0.38
    datasets
    0.37
     Attachment
    0.37
     پرا
    0.37
    購
    0.37
    POSITIVE LOGITS
     referee
    2.61
     referees
    2.42
     Referee
    2.36
    Referee
    2.27
     officiating
    2.03
     umpire
    1.98
     adjud
    1.63
    ผู้ตัดสิน
    1.61
     offici
    1.56
     adjudication
    1.55
    Activations Density 0.105%

    No Known Activations