© 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. 23912
    Prev
    Next
    INDEX
    Explanations

    Homeland Security and terrorism

    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
     armies
    -0.88
    覃
    -0.77
     army
    -0.77
     military
    -0.75
     Armies
    -0.75
     shelling
    -0.74
     mengadakan
    -0.72
     bahç
    -0.72
     geçmiş
    -0.71
     esferas
    -0.71
    POSITIVE LOGITS
     Terror
    0.99
     terrorist
    0.99
     terror
    0.98
     terrorism
    0.97
    terror
    0.94
    Terror
    0.92
     pino
    0.90
    terrorism
    0.83
     Terrorism
    0.82
     terrorists
    0.81
    Activations Density 0.025%

    No Known Activations