© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60505
    Prev
    Next
    INDEX
    Explanations

    North Korea and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    க்க
    -0.89
     estacionamiento
    -0.85
    equalsIgnoreCase
    -0.84
    photon
    -0.73
     synaptic
    -0.72
    mmol
    -0.71
    interrupt
    -0.70
     photon
    -0.69
    kB
    -0.69
     וְ
    -0.69
    POSITIVE LOGITS
     Pyongyang
    1.77
     North
    1.29
    North
    1.17
     Chol
    1.05
     DPR
    1.02
     Kim
    0.98
     Workers
    0.90
     NK
    0.89
     UNC
    0.89
     Jong
    0.86
    Activations Density 0.023%

    No Known Activations