© 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. 53-GEMMASCOPE-2-RES-262K
    7. 13026
    Prev
    Next
    INDEX
    Explanations

    sales, discounts, and promotions

    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_53_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
     transduction
    0.39
     metaphysics
    0.38
    指示
    0.38
    derick
    0.38
    議論
    0.37
    著作
    0.37
    }+(\
    0.36
    格納
    0.36
    Complexity
    0.36
     Instrumentation
    0.36
    POSITIVE LOGITS
     discounts
    2.72
     discount
    2.48
     promotions
    2.28
     Discounts
    2.28
    discount
    2.19
     discounted
    2.16
    Discount
    2.14
     할인
    2.13
     Discount
    2.09
     descuentos
    2.05
    Activations Density 0.074%

    No Known Activations