© 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. 20120
    Prev
    Next
    INDEX
    Explanations

    Nike and Adidas sneakers

    np_acts-logits-general · gemini-2.5-flash-lite

    Nike, sneakers, and streetwear

    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
     baryons
    0.53
    诵
    0.50
     ovarian
    0.49
     heparin
    0.49
    べき
    0.48
    ReaderWriter
    0.48
    ረስ
    0.47
     recursive
    0.47
    ೇವಿನ
    0.46
    軎
    0.46
    POSITIVE LOGITS
     Nike
    1.45
     nike
    1.43
     adidas
    1.32
     sneaker
    1.27
    nike
    1.23
    Nike
    1.23
     Adidas
    1.22
     NIKE
    1.20
    adidas
    1.19
     sneakers
    1.17
    Activations Density 0.111%

    No Known Activations