© 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. 83392
    Prev
    Next
    INDEX
    Explanations

    business, finance, marketing, operations

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

    The neuron strongly responds to segments listing business‐school offerings or course/major codes (e.g. names and acronyms of majors, “offers,” “choose from,” parenthesized lists of programs).

    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
    énieur
    -0.79
     plantea
    -0.75
    ﻲ
    -0.74
    守護
    -0.73
    дый
    -0.72
    コーディネート
    -0.72
    phylaxis
    -0.71
     Monthly
    -0.71
    HANDLE
    -0.71
    ѫ
    -0.71
    POSITIVE LOGITS
     marketing
    1.70
     finance
    1.48
    Marketing
    1.34
     Marketing
    1.29
    marketing
    1.13
     Finance
    1.11
    finance
    1.11
     operations
    1.08
     марке
    1.06
     strategy
    1.04
    Activations Density 0.021%

    No Known Activations