© 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. 34-GEMMASCOPE-RES-131K
    7. 92087
    Prev
    Next
    INDEX
    Explanations

    sell-off, declines, sell, dumped

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

    The neuron primarily detects numeric expressions—especially financial figures, percentages, and other quantitative data in a market context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     bullish
    -0.93
    ↗
    -0.83
    🛥
    -0.81
    ires
    -0.78
     cations
    -0.78
     miracles
    -0.77
     futu
    -0.77
    bull
    -0.77
    mousemove
    -0.77
     squeak
    -0.76
    POSITIVE LOGITS
     sell
    2.94
     selling
    2.53
    Sell
    2.25
     Sell
    2.25
    Selling
    2.14
     sells
    2.13
     Selling
    2.06
    sell
    2.03
    selling
    1.98
    SELL
    1.96
    Activations Density 0.035%

    No Known Activations