© 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. 93339
    Prev
    Next
    INDEX
    Explanations

    military expeditions or wars

    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
    積
    -0.77
     perspectivas
    -0.74
    VAT
    -0.72
     Calhoun
    -0.70
    mediaType
    -0.69
     generates
    -0.69
    strzy
    -0.68
     typically
    -0.68
    navBar
    -0.68
     Generates
    -0.66
    POSITIVE LOGITS
     Expedition
    1.04
     overseas
    1.03
     attached
    0.99
     оттен
    0.95
    attached
    0.93
    mentioned
    0.87
    Overseas
    0.85
     theatres
    0.83
     expedition
    0.83
     SECOND
    0.82
    Activations Density 0.039%

    No Known Activations