© 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. 2616
    Prev
    Next
    INDEX
    Explanations

    specializing in companies and agencies

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

    what companies specialize in

    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
     schoolchildren
    0.46
     तलब
    0.46
     zumindest
    0.45
     unprotected
    0.45
     অন্তত
    0.45
    报错
    0.44
     നഷ്ട
    0.44
    嘱
    0.43
     부탁
    0.43
    少なくとも
    0.43
    POSITIVE LOGITS
     specializing
    1.99
     specializes
    1.95
     specialize
    1.93
     specialising
    1.84
     specialise
    1.80
     specialises
    1.76
     специали
    1.55
     specialization
    1.55
     especializada
    1.45
     especializado
    1.42
    Activations Density 0.627%

    No Known Activations