© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9502
    Prev
    Next
    INDEX
    Explanations

    online shopping

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

    The neuron fires strongly on tokens involved in shopping or retail contexts (e.g. “shop,” “shopping,” “online,” “cart,” hyphenated shop-in-shop, etc.), so it’s looking for mentions of shopping or related commerce activity.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    datable
    -1.80
     and
    -1.76
    ーション
    -1.57
     enrique
    -1.54
     forthcoming
    -1.54
    );
    -1.52
     gratuito
    -1.52
    так
    -1.52
     campesinos
    -1.51
    AÇÃO
    -1.49
    POSITIVE LOGITS
    ↵↵
    2.14
     schmerz
    1.75
     tutte
    1.74
     dizaine
    1.73
     tormented
    1.70
     pequeño
    1.70
    
    1.66
     pudieron
    1.63
    ies
    1.62
     filós
    1.61
    Activations Density 0.016%

    No Known Activations