© 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. 34-GEMMASCOPE-RES-131K
    7. 2819
    Prev
    Next
    INDEX
    Explanations

    firms or companies

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

    The neuron responds to economics/business terminology—words referring to markets, competition, firms, pricing, monopoly, and related domain-specific concepts.

    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
    ഃ
    -0.82
    tistas
    -0.81
    (:)
    -0.77
     progn
    -0.75
    uw
    -0.75
    ervices
    -0.73
    riders
    -0.72
     Niel
    -0.72
    ∷
    -0.72
    ียม
    -0.70
    POSITIVE LOGITS
     firms
    4.41
     firm
    3.97
     Firms
    3.20
    firm
    3.06
     Firm
    2.98
    Firm
    2.80
    fir
    2.27
    Fir
    2.25
     firma
    2.19
     фир
    2.17
    Activations Density 0.024%

    No Known Activations