© 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. 108789
    Prev
    Next
    INDEX
    Explanations

    Pakistan followed by names

    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
     altogether
    -0.97
     onView
    -0.85
     losers
    -0.83
    ibrill
    -0.83
     bezeichneter
    -0.81
     liners
    -0.80
    ştır
    -0.78
    TERY
    -0.76
     devoid
    -0.76
     fabulous
    -0.75
    POSITIVE LOGITS
    Pakistan
    1.03
     پاکستان
    0.94
    continent
    0.94
    🇵
    0.93
     στρα
    0.93
     Rangers
    0.92
     Pakistan
    0.90
     rangers
    0.89
     Febru
    0.87
     Islamabad
    0.86
    Activations Density 0.016%

    No Known Activations