© 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. 7105
    Prev
    Next
    INDEX
    Explanations

    US government and diplomacy

    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
    зика
    -0.99
    SceneManagement
    -0.91
    hkan
    -0.90
     valent
    -0.90
    一抹
    -0.89
    allow
    -0.86
     oublié
    -0.85
    paccio
    -0.85
    riterion
    -0.84
     expuls
    -0.84
    POSITIVE LOGITS
     government
    1.52
     Government
    1.27
     involvement
    1.09
     leadership
    1.07
     presence
    1.05
    因素
    1.04
     interests
    0.99
     role
    0.98
     administration
    0.97
     policy
    0.94
    Activations Density 0.044%

    No Known Activations