© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 18677
    Prev
    Next
    INDEX
    Explanations

    discount

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

    academic, student, or researcher discounts

    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
    表情
    0.42
     안정
    0.42
     resh
    0.39
    reshape
    0.39
     endurance
    0.39
     trải
    0.39
    詭
    0.39
    ឿង
    0.38
    MetaData
    0.38
     reshape
    0.38
    POSITIVE LOGITS
     Discount
    1.07
     discount
    1.06
    Discount
    1.01
     할인
    0.98
     discounts
    0.97
     discounted
    0.96
     descuento
    0.96
    discount
    0.95
    優惠
    0.93
    割引
    0.88
    Activations Density 0.127%

    No Known Activations