© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12929
    Prev
    Next
    INDEX
    Explanations

    employee and employer rights

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

    The neuron strongly activates on corporate‐style promotional copy—especially marketing language describing employee benefit plans and HR service offerings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鳖
    0.57
     эко
    0.56
    ЗО
    0.55
    仪器
    0.55
     экспеди
    0.55
     PROFESSION
    0.54
     কোষ
    0.54
    ূ
    0.52
    专业
    0.52
    レンズ
    0.52
    POSITIVE LOGITS
     Employee
    2.03
     employee
    2.02
    Employee
    1.99
    employee
    1.95
     employer
    1.81
     Employees
    1.80
    Employees
    1.80
     Employer
    1.73
    employees
    1.73
     employees
    1.71
    Activations Density 0.479%

    No Known Activations