© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10700
    Prev
    Next
    INDEX
    Explanations

    Bloomberg financial news and data

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

    The neuron strongly fires on tokens from financial‐market reporting—e.g. stock indexes, futures, Treasury yields, currency moves and their numeric values—so it’s looking for financial-market data references.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "["
    0.71
    '
    0.63
     "[
    0.63
    '،
    0.60
    bollywood
    0.60
     "/
    0.59
     "("
    0.59
    szlig
    0.59
     مسلمان
    0.58
    pośred
    0.58
    POSITIVE LOGITS
     Bloomberg
    1.42
    Bloomberg
    1.25
     BLO
    0.95
    bloom
    0.91
     bloom
    0.82
    🤭
    0.75
     Bloom
    0.75
    BLO
    0.73
     metaverse
    0.72
     Biden
    0.71
    Activations Density 0.052%

    No Known Activations