© 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. 34497
    Prev
    Next
    INDEX
    Explanations

    conglomerates and holding companies

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

    The neuron flags tokens that occur in sentences describing a company’s hierarchy and size—e.g. “is a subsidiary of,” “largest,” and the quantitative figures that follow.

    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
     QUART
    -0.76
    ښ
    -0.76
     アイテム
    -0.75
    cessor
    -0.74
    SOCI
    -0.74
    chenke
    -0.73
    Blame
    -0.73
    aryn
    -0.73
     basso
    -0.73
    ſed
    -0.71
    POSITIVE LOGITS
     conglomerate
    2.19
     conglomer
    1.72
     group
    1.52
     Group
    1.45
    group
    1.27
     diversified
    1.21
    グループ
    1.20
     Cong
    1.19
     diversification
    1.13
     Grupo
    1.11
    Activations Density 0.031%

    No Known Activations