© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 51891
    Prev
    Next
    INDEX
    Explanations

    shirt or shirts

    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_65k_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
     eyewear
    0.51
     костю
    0.49
     roupas
    0.48
     одежда
    0.47
     handbag
    0.45
     পোশাক
    0.45
    옷
    0.45
     옷
    0.44
     аксессу
    0.44
     roupa
    0.44
    POSITIVE LOGITS
     shirt
    0.98
     Shirt
    0.86
     shirts
    0.85
     Shirts
    0.82
    Shirt
    0.80
    shirt
    0.80
    シャツ
    0.73
    shirts
    0.71
    Shirts
    0.66
     शर्ट
    0.65
    Activations Density 0.045%

    No Known Activations