© 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. 41-GEMMASCOPE-2-RES-262K
    7. 63920
    Prev
    Next
    INDEX
    Explanations

    refunds

    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_all/layer_41_width_262k_l0_big
    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
    acariy
    0.40
     kriy
    0.40
    illors
    0.40
    ellite
    0.39
     প্রিয়
    0.38
    шенный
    0.38
    佉
    0.38
     ভারতীয়
    0.37
    partials
    0.37
    馕
    0.37
    POSITIVE LOGITS
     refunds
    1.52
     refund
    1.51
    Refund
    1.41
     Refunds
    1.39
     Refund
    1.34
    refund
    1.31
     refunded
    1.23
     rebate
    1.13
     rebates
    1.13
     reembolso
    0.93
    Activations Density 0.002%

    No Known Activations