© 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. 102886
    Prev
    Next
    INDEX
    Explanations

    letters of credit

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

    The neuron is keyed to formal financial‐instrument and banking jargon—terms like bank guarantees, letters of credit (LOC), SBLC, lease/purchase arrangements, and related numeric deal details.

    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
    HAC
    -0.85
     Foire
    -0.77
    ToJson
    -0.75
     Epidemio
    -0.75
     hydra
    -0.75
     preach
    -0.73
     moot
    -0.73
    präche
    -0.72
     خیر
    -0.71
     Franse
    -0.71
    POSITIVE LOGITS
     letters
    1.84
     Letters
    1.78
     letter
    1.66
     Letter
    1.64
    Letters
    1.49
    Letter
    1.48
    letter
    1.41
    letters
    1.31
     LC
    1.16
     documentary
    1.10
    Activations Density 0.011%

    No Known Activations