© 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. 47604
    Prev
    Next
    INDEX
    Explanations

    graph.js

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

    The neuron fires on code or text referring to the Interactive Brokers API—specifically mentions of IB, IBWrapper, EClientSocket, ScannerSubscription, and related class/module names.

    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
     Isn
    -1.41
     probabilmente
    -1.25
    UPAC
    -1.20
     injustices
    -1.19
    。「
    -1.18
    :「
    -1.16
    。“
    -1.13
    tivis
    -1.13
    ată
    -1.12
    
    -1.11
    POSITIVE LOGITS
    を重ね
    1.28
     mourn
    1.23
    糴
    1.15
     ruso
    1.13
    лио
    1.13
    をします
    1.11
     chłod
    1.11
    <bos>
    1.11
     ouvre
    1.09
     рекомен
    1.08
    Activations Density 0.030%

    No Known Activations