© 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. 62985
    Prev
    Next
    INDEX
    Explanations

    World War II contexts

    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
     merawat
    -1.07
     discernible
    -0.97
     extraordinarily
    -0.94
     before
    -0.92
     Seeing
    -0.89
     embracing
    -0.89
     empathetic
    -0.87
     Thats
    -0.86
     invigor
    -0.86
     unparalleled
    -0.86
    POSITIVE LOGITS
     avon
    1.14
     erat
    1.07
     proposent
    1.05
     anunciou
    1.04
     communiquez
    1.04
     possess
    1.03
     palav
    1.02
     concernant
    0.96
     pesso
    0.96
     rowspan
    0.96
    Activations Density 0.014%

    No Known Activations