© 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. 53-GEMMASCOPE-2-RES-262K
    7. 10032
    Prev
    Next
    INDEX
    Explanations

    wrestling and wrestling leagues

    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_53_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
     Marginal
    0.48
    袤
    0.48
    🎷
    0.47
     Iterate
    0.46
     Delft
    0.46
     Laplace
    0.45
     ratione
    0.45
    😿
    0.45
    苺
    0.44
     Cartesian
    0.43
    POSITIVE LOGITS
     wrestling
    2.30
     wrestlers
    2.27
     wrestler
    2.13
     WWE
    2.06
     Wrestling
    1.99
    WWE
    1.99
     wrestled
    1.88
     Wrestle
    1.87
     wrestle
    1.84
     Wrest
    1.78
    Activations Density 0.012%

    No Known Activations