© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13468
    Prev
    Next
    INDEX
    Explanations

    cancellation and refund

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

    cancel, refund, failed, or abort

    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
    いている
    0.41
    
    0.40
    増や
    0.40
    locationX
    0.39
    いています
    0.38
    ramatta
    0.37
     mammary
    0.36
     Waugh
    0.36
     قدیم
    0.36
    扁
    0.36
    POSITIVE LOGITS
     cancellation
    1.02
     cancel
    1.01
     refund
    0.98
     cancellations
    0.98
     cancelled
    0.97
     रद्द
    0.96
     canceling
    0.95
     refunded
    0.94
     Cancellation
    0.94
     canceled
    0.93
    Activations Density 0.143%

    No Known Activations