© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64676
    Prev
    Next
    INDEX
    Explanations

    armenian places and organizations

    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
     Turkey
    -1.30
     Turkish
    -1.21
    Turkey
    -1.12
    Turkish
    -1.05
     Istanbul
    -0.94
     turkey
    -0.93
     Azerbai
    -0.90
     Turks
    -0.90
    土耳其
    -0.89
     turkish
    -0.88
    POSITIVE LOGITS
     Арме
    0.81
     Armenia
    0.79
     cív
    0.74
    Armenia
    0.74
     coloridas
    0.74
    phosphate
    0.73
    葺
    0.73
     Eduard
    0.72
    bonded
    0.71
     Holmes
    0.71
    Activations Density 0.006%

    No Known Activations