© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2095
    Prev
    Next
    INDEX
    Explanations

    employee and workplace relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_17_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
     cxd
    1.12
    彗
    1.01
    скет
    0.99
    オク
    0.97
     അമേ
    0.96
     Rivière
    0.94
    壤
    0.93
     Judah
    0.92
     گول
    0.91
    垓
    0.90
    POSITIVE LOGITS
     Employee
    4.26
     employee
    4.21
    Employee
    4.10
    employee
    3.94
     employees
    3.86
     Employees
    3.76
    Employees
    3.72
     workplace
    3.66
    employees
    3.61
     employer
    3.58
    Activations Density 1.697%

    No Known Activations