© 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. 22-GEMMASCOPE-RES-131K
    4. 79551
    Prev
    Next
    INDEX
    Explanations

    stock market news or technical descriptions

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

    The neuron is specialized to pick out stock‐market tickers and numeric financial figures (e.g. exchange symbols like “NYSE” or “AAPL” and numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     ministra
    -1.14
     tacón
    -1.13
     perfekte
    -1.09
     not
    -1.08
     itens
    -1.07
    ⊖
    -1.03
    zondere
    -1.03
    _${
    -1.00
     tibur
    -0.99
     their
    -0.98
    POSITIVE LOGITS
     we
    1.29
     cubierto
    1.23
     juzgar
    1.22
     одному
    1.20
     serán
    1.14
    estinations
    1.13
    genöss
    1.12
     okazji
    1.10
    ogenous
    1.09
    ڻ
    1.09
    Activations Density 0.000%

    No Known Activations