© 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. 102706
    Prev
    Next
    INDEX
    Explanations

    banking and sanctions

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

    This neuron detects mentions of economic sanctions or related financial restrictions.

    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
    lipop
    -0.84
    expense
    -0.79
     preocupado
    -0.75
     промо
    -0.72
    ються
    -0.72
    Ȉ
    -0.71
    連続
    -0.71
    感を
    -0.70
    ſto
    -0.70
    &
    -0.69
    POSITIVE LOGITS
     banking
    1.09
     barter
    1.03
     Banking
    1.00
     sanctions
    0.97
     अर्थ
    0.96
    banking
    0.94
    compliance
    0.94
     Siemens
    0.93
    ಿದೆ
    0.93
     transactions
    0.92
    Activations Density 0.011%

    No Known Activations