© 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. 32563
    Prev
    Next
    INDEX
    Explanations

    military operations and locations

    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
    Ή
    -1.02
    Με
    -0.89
    Participants
    -0.89
     paramedics
    -0.88
    Neighbours
    -0.87
     bombar
    -0.83
     noexcept
    -0.82
    átula
    -0.82
     diskusi
    -0.81
    Données
    -0.81
    POSITIVE LOGITS
     friendly
    1.10
     morta
    0.98
     RPG
    0.97
     Bravo
    0.92
    friendly
    0.90
     Chinook
    0.90
     Provincial
    0.88
     walked
    0.88
     Friendly
    0.86
     kinetic
    0.85
    Activations Density 0.036%

    No Known Activations