© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14732
    Prev
    Next
    INDEX
    Explanations

    governmental bureaus and agencies

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

    government and administrative structures

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

    government bureaucracy

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
     provide
    0.59
     tavern
    0.58
     നിയ
    0.56
     zi
    0.55
     d
    0.51
     kontrol
    0.49
     twor
    0.49
     n
    0.48
     s
    0.48
     provides
    0.48
    POSITIVE LOGITS
     bureaucr
    0.94
     bureaucratic
    0.83
     bureaucracy
    0.82
     bureaucrats
    0.80
    職員
    0.70
     bureaus
    0.70
    सरकारी
    0.68
     सरकारी
    0.68
     অফিসে
    0.66
     কর্মকর্তা
    0.64
    Activations Density 0.327%

    No Known Activations