© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15789
    Prev
    Next
    INDEX
    Explanations

    tennis player, serve, balls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    Celeron
    0.52
    Ꮔ
    0.46
    苄
    0.45
    觀塘
    0.45
     ఉత్ప
    0.44
    Walmart
    0.44
    嶺
    0.44
    Clock
    0.43
     bottlene
    0.43
     ricon
    0.43
    POSITIVE LOGITS
     tennis
    1.51
     Tennis
    1.44
     tenis
    1.33
    tennis
    1.29
    Tennis
    1.27
     टेनिस
    1.09
    🎾
    1.06
     Wimbledon
    1.02
     теннис
    1.01
     Kyrgios
    0.96
    Activations Density 0.010%

    No Known Activations