© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 129948
    Prev
    Next
    INDEX
    Explanations

    The neuron detects uppercase stock‐ticker symbols (exchange codes) in financial text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    company stock tickers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     of
    -1.57
    のだろう
    -1.42
     that
    -1.38
     your
    -1.35
     distritos
    -1.31
    んですよ
    -1.28
     tratto
    -1.23
    ())).
    -1.20
     filós
    -1.19
     from
    -1.16
    POSITIVE LOGITS
    がありますが
    1.54
    があるので
    1.41
    <bos>
    1.38
    もあって
    1.34
    erobic
    1.30
    もありますが
    1.30
    ztes
    1.27
    そして
    1.23
    があり
    1.20
    があります
    1.20
    Activations Density 0.011%

    No Known Activations