© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 4083
    Prev
    Next
    INDEX
    Explanations

    financial performance up or down

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

    The neuron specializes in spotting quantitative financial performance metrics—numbers, percentages, returns, yields, and similar statistical figures in investment contexts.

    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
    TestBed
    -0.82
    を受けた
    -0.79
    HIGHLIGHTS
    -0.77
    啕
    -0.77
    selas
    -0.76
    ӑ
    -0.75
    IARC
    -0.74
    ğından
    -0.74
     аренду
    -0.73
     denuncias
    -0.72
    POSITIVE LOGITS
     performance
    1.63
     returns
    1.42
    PERFORMANCE
    1.30
    performance
    1.30
     outperform
    1.28
     performances
    1.24
    returns
    1.23
     return
    1.19
    Performance
    1.15
    gains
    1.13
    Activations Density 0.020%

    No Known Activations