© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1525
    Prev
    Next
    INDEX
    Explanations

    World Cup Championships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aghan
    1.70
     مخط
    1.31
    alog
    1.25
    odont
    1.18
    tta
    1.17
    貽
    1.16
    と思い
    1.15
     fonti
    1.14
    ḫ
    1.14
    қан
    1.13
    POSITIVE LOGITS
     competitions
    2.73
     Competition
    2.71
     compétition
    2.69
     World
    2.62
     Cup
    2.60
     Championships
    2.56
    World
    2.55
     competition
    2.54
    Competition
    2.51
     Championship
    2.45
    Activations Density 0.061%

    No Known Activations