© 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. 62966
    Prev
    Next
    INDEX
    Explanations

    Switzerland and Zürich

    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
    **********/
    -0.80
     軍
    -0.71
     red
    -0.71
    endidikan
    -0.69
     sleep
    -0.68
    dehyde
    -0.68
     Kräfte
    -0.68
     الأمير
    -0.66
     Nathan
    -0.65
     Gründung
    -0.64
    POSITIVE LOGITS
     Switzerland
    0.91
     Jardin
    0.85
    Switzerland
    0.84
     Suisse
    0.81
     swiss
    0.80
     cantons
    0.79
     Chur
    0.79
     corrector
    0.77
    äldrar
    0.75
     گذشته
    0.72
    Activations Density 0.019%

    No Known Activations