© 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. 109329
    Prev
    Next
    INDEX
    Explanations

    Regulation T, Exchange Act, SEC

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

    The neuron is detecting legal or regulatory section and rule citations—i.e. sequences of numbers (and adjoining punctuation/letters) that identify statutes, rules, or code sections.

    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
     warmth
    -0.77
    giti
    -0.76
    FAMIL
    -0.76
    ituary
    -0.75
    źdz
    -0.75
     menn
    -0.74
    РС
    -0.73
    官网
    -0.72
     cabriolet
    -0.72
    ثيق
    -0.72
    POSITIVE LOGITS
     Rule
    1.10
     Exchange
    1.03
     SEC
    1.00
    Rule
    0.90
    Exchange
    0.89
    交换
    0.85
    SEC
    0.81
     RULE
    0.75
     exchange
    0.75
     Act
    0.75
    Activations Density 0.022%

    No Known Activations