© 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. 22-GEMMASCOPE-RES-131K
    7. 33723
    Prev
    Next
    INDEX
    Explanations

    business entities or subsidiaries

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

    The neuron flags mentions of corporate entities and their ownership, investment, or subsidiary relationships.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     feel
    -1.17
    Przeczytaj
    -1.13
     use
    -1.11
     junto
    -1.09
    beforeAll
    -1.08
    ׇ
    -1.08
     especially
    -1.06
     help
    -1.06
     have
    -1.04
     inspired
    -1.03
    POSITIVE LOGITS
     subsidiaries
    1.77
    ּוֹ
    1.60
     companies
    1.58
     company
    1.57
     entities
    1.55
     السياس
    1.44
    ִּ
    1.36
     entity
    1.30
     coussin
    1.27
     exercices
    1.26
    Activations Density 0.042%

    No Known Activations