© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118146
    Prev
    Next
    INDEX
    Explanations

    derivatives and credit instruments

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

    This neuron fires strongly on formal, capitalized headings, labels, and acronyms (e.g. “Payment Date,” “Section,” “Transaction,” “CDO,” “ISDA”) typical of legal or financial documents.

    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
    ‍
    -0.81
    ž
    -0.80
    #
    -0.79
     Pegasus
    -0.79
     Dayton
    -0.77
    cherche
    -0.77
     Arlington
    -0.72
    ACTION
    -0.72
     Roberts
    -0.72
     Gases
    -0.72
    POSITIVE LOGITS
     CDS
    1.32
    CDS
    1.06
     insuring
    1.02
     cds
    1.01
     insurance
    0.98
    cds
    0.91
    保険
    0.84
    idth
    0.83
     reference
    0.80
     INSURANCE
    0.80
    Activations Density 0.017%

    No Known Activations