© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3251
    Prev
    Next
    INDEX
    Explanations

    consumer returns and exceptions

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

    This neuron detects segments describing purchase-related policies—especially return, cancellation, and buyer-rights language with deadlines and conditions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verletzt
    -0.80
    Erfolge
    -0.78
    태
    -0.70
    皙
    -0.70
     readjust
    -0.70
     conoci
    -0.68
    Marx
    -0.68
    isometric
    -0.66
     secar
    -0.66
    uffy
    -0.66
    POSITIVE LOGITS
     consumer
    1.52
     consumers
    1.42
    consumer
    1.29
     Consumer
    1.19
     потреби
    1.16
    Consumer
    1.14
    Consumers
    1.12
     Consumers
    1.08
     consumidores
    1.05
     cooling
    1.05
    Activations Density 0.006%

    No Known Activations