© 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-262K
    7. 12552
    Prev
    Next
    INDEX
    Explanations

    store, staff, and shopping

    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
    Not in Any Lists

    No Comments

    Negative Logits
     commanded
    0.40
     명령
    0.39
     comandos
    0.38
    ႇ
    0.38
     comando
    0.38
    餐
    0.38
     इस्ती
    0.38
    лянчук
    0.37
     इस्तीफा
    0.37
     Diary
    0.37
    POSITIVE LOGITS
    店内
    1.43
     shopping
    1.36
     salesperson
    1.33
     salespeople
    1.33
     shoppers
    1.30
     shop
    1.29
    店
    1.29
     sales
    1.27
     দোকানে
    1.27
     Shopping
    1.27
    Activations Density 0.025%

    No Known Activations