© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12808
    Prev
    Next
    INDEX
    Explanations

    stock exchange identifiers

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

    The neuron detects stock‐market tickers and exchange abbreviations (e.g. TSX, Nasdaq, SE HK, NYSE).

    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
     that
    -2.05
     opio
    -1.34
     canzone
    -1.30
     カレー
    -1.28
     surrounding
    -1.24
     xhr
    -1.23
    紲
    -1.23
     to
    -1.23
     bellissima
    -1.23
     scoperta
    -1.23
    POSITIVE LOGITS
    '
    1.38
    名は
    1.24
     ۱۹
    1.18
     verdieping
    1.16
    \'
    1.13
    idee
    1.13
    部に
    1.12
    钻石
    1.12
     robić
    1.12
    چند
    1.11
    Activations Density 0.028%

    No Known Activations