© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 173
    Prev
    Next
    INDEX
    Explanations

    present value and discount

    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
    কানিক্যাল
    0.44
    纮
    0.43
    齐全
    0.41
    骖
    0.41
     sınır
    0.40
    RestorePolicy
    0.40
    ابس
    0.40
    厨
    0.40
    ിച്ചി
    0.39
    ક્ષા
    0.39
    POSITIVE LOGITS
     discounted
    1.63
     discounting
    1.51
    discount
    1.42
     discount
    1.36
     Discount
    1.34
    Discount
    1.32
     present
    1.20
     DISCOUNT
    1.17
    Present
    1.13
    present
    1.12
    Activations Density 0.015%

    No Known Activations