© 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. 49371
    Prev
    Next
    INDEX
    Explanations

    the world

    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
     then
    -1.02
     anyway
    -1.00
    本日の
    -0.98
    今日も
    -0.97
     anyways
    -0.95
    ก็
    -0.94
     також
    -0.93
     også
    -0.92
    Сайт
    -0.88
    まず
    -0.87
    POSITIVE LOGITS
    同様に
    0.90
    виа
    0.87
     Процитовано
    0.82
    进一步
    0.81
    !
    0.78
     tiegħ
    0.76
     st
    0.75
     chaque
    0.74
     bí
    0.73
    guila
    0.72
    Activations Density 0.094%

    No Known Activations