© 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. 34-GEMMASCOPE-RES-131K
    7. 108988
    Prev
    Next
    INDEX
    Explanations

    tariffs and duties

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

    The neuron activates on mentions of tariffs (e.g. the word “tariff” or “tariffs”).

    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
     میر
    -0.80
    ativen
    -0.79
     pintar
    -0.77
    Produzione
    -0.76
    acão
    -0.75
     ウルトラ
    -0.74
    osh
    -0.73
    detect
    -0.73
    Distribuzione
    -0.72
     etapa
    -0.71
    POSITIVE LOGITS
     tariffs
    1.85
     tariff
    1.84
     rates
    1.48
     Tariff
    1.26
    tar
    1.25
     rate
    1.24
     duty
    1.17
     levied
    1.16
     protective
    1.11
     Tar
    1.09
    Activations Density 0.012%

    No Known Activations