© 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. 31097
    Prev
    Next
    INDEX
    Explanations

    SWIFT codes and numbers

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

    The main thing this neuron does is find mentions of international bank transfer details—especially SWIFT codes and related payment or currency‐transfer information.

    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
     Consul
    -0.74
    scriptId
    -0.71
     multipliers
    -0.68
     rewritten
    -0.68
    ో
    -0.66
     Cookies
    -0.65
    は無
    -0.65
    Tir
    -0.65
     imperson
    -0.63
    Buena
    -0.63
    POSITIVE LOGITS
     Swift
    1.59
     SWIFT
    1.59
    Swift
    1.33
     messaging
    1.22
    swift
    1.14
     swift
    1.08
     messages
    1.05
     message
    0.99
    Messaging
    0.96
    SW
    0.95
    Activations Density 0.035%

    No Known Activations