© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 242892
    Prev
    Next
    INDEX
    Explanations

    Olympic Games

    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_31_width_262k_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
    ي
    0.51
    también
    0.50
    荑
    0.48
    stained
    0.45
    Sach
    0.45
     ナ
    0.45
    を使って
    0.45
     Masse
    0.45
    への
    0.43
    occ
    0.43
    POSITIVE LOGITS
     округу
    0.54
     enige
    0.48
    犷
    0.47
     destacar
    0.47
     lobortis
    0.45
    典型
    0.44
    最具
    0.44
    ızlı
    0.44
    idel
    0.44
     matric
    0.44
    Activations Density 0.000%

    No Known Activations