© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 12877
    Prev
    Next
    INDEX
    Explanations

    Olympic Games and related events

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Norton
    0.48
     Regulator
    0.47
    长老
    0.45
     PWMA
    0.44
     Aspergillus
    0.42
    行業
    0.40
    ுகள்
    0.40
    俚
    0.39
     Controller
    0.39
     deacetyl
    0.39
    POSITIVE LOGITS
     Olympic
    2.45
    Olympic
    2.30
     Olympics
    2.20
     ओलंपिक
    2.13
     olymp
    2.09
    奥运
    1.99
     olimp
    1.97
     olímp
    1.85
     Олимпий
    1.84
     Olimpi
    1.76
    Activations Density 0.008%

    No Known Activations