© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1302
    Prev
    Next
    INDEX
    Explanations

    department

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

    department in organizational contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
     Proxy
    0.55
     proximal
    0.50
     proxy
    0.47
     Prox
    0.45
     isomers
    0.43
    PROXY
    0.42
     సినీ
    0.42
    𐰼
    0.41
    Proxy
    0.41
     proxies
    0.41
    POSITIVE LOGITS
     Department
    4.03
     department
    4.03
    Department
    3.94
    department
    3.86
     DEPARTMENT
    3.69
     Departments
    3.56
    DEPARTMENT
    3.53
     Dept
    3.50
     departments
    3.48
     डिपार्टमेंट
    3.42
    Activations Density 0.253%

    No Known Activations