© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117190
    Prev
    Next
    INDEX
    Explanations

    Burundi, Rwanda, East Africa

    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
     Middel
    -0.85
    ChildIndex
    -0.77
    Père
    -0.74
    ➷
    -0.72
     Tapa
    -0.71
     Meksiko
    -0.69
     pik
    -0.67
     Caracas
    -0.66
     Hals
    -0.66
    endente
    -0.66
    POSITIVE LOGITS
     Rwanda
    1.95
     Rwand
    1.71
    Rwanda
    1.66
     Kigali
    1.51
     Burundi
    1.23
     genocide
    1.23
     Genocide
    1.09
    🇷
    0.98
     Kag
    0.94
     methane
    0.91
    Activations Density 0.021%

    No Known Activations