© 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. 6722
    Prev
    Next
    INDEX
    Explanations

    insider trading and securities filings

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

    This neuron activates on passages describing stock‐market or financial trading activity, with high numeric and monetary terminology.

    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
     المقد
    -0.85
     Vat
    -0.84
    Logo
    -0.82
    卡
    -0.81
    Hab
    -0.79
    Prote
    -0.78
    Tea
    -0.77
    Ant
    -0.77
    Intro
    -0.76
     CVE
    -0.76
    POSITIVE LOGITS
     insider
    1.83
     trading
    1.45
    insider
    1.41
     Insider
    1.30
    Insider
    1.23
     securities
    1.17
    trading
    1.17
     trades
    1.14
     traders
    1.09
     insiders
    1.09
    Activations Density 0.014%

    No Known Activations