© 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. 10-GEMMASCOPE-RES-131K
    4. 47977
    Prev
    Next
    INDEX
    Explanations

    derivatives and financial instruments

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

    The neuron detects mentions of financial or trading jargon, especially terms related to complex financial instruments (e.g., derivatives, trading, financial markets).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    <em>
    -1.27
    目次
    -1.22
    没有人
    -1.21
     Posteriormente
    -1.20
    ciąg
    -1.20
    ONLY
    -1.17
    )
    -1.16
     Manten
    -1.16
    <i>
    -1.15
     Mientras
    -1.15
    POSITIVE LOGITS
     acuerdos
    1.53
    ită
    1.38
    ternut
    1.31
    hees
    1.30
    DidLoad
    1.22
    mueble
    1.22
     într
    1.21
     atractiva
    1.19
    IDS
    1.18
     terceros
    1.16
    Activations Density 0.040%

    No Known Activations