© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15581
    Prev
    Next
    INDEX
    Explanations

    refunds and returns

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

    refund and return resolution

    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_16k_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
    oblast
    0.48
    ambahan
    0.45
    addEdge
    0.44
     verteilt
    0.43
    <unused75>
    0.42
    เชสเตอร์
    0.42
     стар
    0.41
    forbidden
    0.41
     маршру
    0.41
    
    0.41
    POSITIVE LOGITS
     refund
    1.30
     refunds
    1.26
     Refund
    1.21
     Refunds
    1.20
    refund
    1.09
     refunded
    1.07
    Refund
    1.06
    返品
    0.83
     refundable
    0.82
     reembolso
    0.80
    Activations Density 0.374%

    No Known Activations