© 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. 108700
    Prev
    Next
    INDEX
    Explanations

    World War

    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
     west
    -1.17
     West
    -1.13
     western
    -1.09
     Western
    -1.09
    west
    -0.98
    WEST
    -0.96
     Westen
    -0.94
    western
    -0.91
    West
    -0.90
     غرب
    -0.87
    POSITIVE LOGITS
     Maserati
    0.92
     Trident
    0.89
    Assertion
    0.84
    ALAM
    0.75
     Industri
    0.74
    enschappelijke
    0.74
     trident
    0.73
     адресу
    0.73
    グラン
    0.69
     QP
    0.68
    Activations Density 0.022%

    No Known Activations