© 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. 92080
    Prev
    Next
    INDEX
    Explanations

    stocks and shares

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

    This neuron detects language describing securities transactions and analyst rating changes (e.g. stock holdings, stake reductions or increases, and rating adjustments).

    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
     like
    -0.94
     veril
    -0.84
     list
    -0.77
    varlak
    -0.76
    运作
    -0.74
     udara
    -0.74
     itens
    -0.73
    oram
    -0.73
    loven
    -0.73
    چھ
    -0.73
    POSITIVE LOGITS
     equities
    1.00
    NASDAQ
    0.95
     stocks
    0.94
    Scalars
    0.89
     oč
    0.88
     stock
    0.87
     poš
    0.84
     preescolar
    0.84
     shares
    0.84
    company
    0.84
    Activations Density 0.007%

    No Known Activations