© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75586
    Prev
    Next
    INDEX
    Explanations

    consumer purchasing decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    oplasmic
    -0.88
     жы
    -0.81
    tack
    -0.79
    miljø
    -0.78
    bidity
    -0.77
    ække
    -0.76
     manpower
    -0.75
    çais
    -0.75
    uchin
    -0.75
     inalámb
    -0.75
    POSITIVE LOGITS
     purchase
    2.64
     purchasing
    2.17
     decision
    2.17
     buying
    2.06
     shopping
    1.99
     purchases
    1.90
    purchase
    1.72
    decision
    1.66
     Purchase
    1.66
    Decision
    1.60
    Activations Density 0.042%

    No Known Activations