© 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. 13244
    Prev
    Next
    INDEX
    Explanations

    stock market news

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

    The neuron selectively activates on financial performance language—terms quantifying or describing earnings, profits, growth, drops, and other market metrics.

    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
     on
    -1.80
     even
    -1.48
     sogar
    -1.46
    vantaged
    -1.37
     only
    -1.34
     many
    -1.28
     muchos
    -1.27
     so
    -1.27
     of
    -1.27
     when
    -1.25
    POSITIVE LOGITS
     fiecare
    1.37
     aussit
    1.27
     ficam
    1.27
     soportes
    1.27
     technisch
    1.24
    perd
    1.23
     technische
    1.22
     cubrir
    1.18
     bedien
    1.18
    鸱
    1.16
    Activations Density 0.066%

    No Known Activations