© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8541
    Prev
    Next
    INDEX
    Explanations

    market trends, prices, and value

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

    The neuron fires on business/financial market jargon—terms like “market,” “price,” “depth,” and “dynamics.”

    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
    旰
    -1.80
    を紹介
    -1.77
    >
    -1.66
    ’.
    -1.62
    泐
    -1.59
    pits
    -1.59
    )),
    -1.51
    цю
    -1.47
     gesagt
    -1.46
    ᾐ
    -1.46
    POSITIVE LOGITS
    0
    2.11
    (
    1.84
    c
    1.84
    b
    1.80
    1.70
    d
    1.64
    '
    1.59
    -
    1.52
    a
    1.52
     diesem
    1.52
    Activations Density 0.028%

    No Known Activations