© 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. 103493
    Prev
    Next
    INDEX
    Explanations

    business, departments, and leadership

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

    The main thing this neuron does is detect phrases that describe business‐oriented services, roles, or functions (e.g. providing, enabling, or fulfilling tasks for the business).

    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
     Patients
    -0.90
     workplace
    -0.88
    signia
    -0.86
     medication
    -0.86
    =#{
    -0.83
     diak
    -0.83
     lampa
    -0.82
     bylo
    -0.82
     ligue
    -0.82
     lampada
    -0.82
    POSITIVE LOGITS
     senior
    1.45
     departments
    1.44
     department
    1.27
     business
    1.23
     team
    1.22
    Senior
    1.20
     Marketing
    1.17
    Marketing
    1.17
     CEO
    1.16
     stakeholders
    1.16
    Activations Density 0.062%

    No Known Activations