© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102529
    Prev
    Next
    INDEX
    Explanations

    war and battle

    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
     criticised
    -0.93
    accum
    -0.90
     criticized
    -0.86
     challenge
    -0.81
     dí
    -0.80
     criticism
    -0.76
     fórmula
    -0.76
     malade
    -0.76
     challeng
    -0.75
     ocze
    -0.75
    POSITIVE LOGITS
     waged
    2.44
     raged
    2.09
     raging
    2.06
     fought
    1.80
    fought
    1.32
     conducted
    1.28
    raging
    1.25
     fier
    1.22
    conducted
    1.17
     wages
    1.13
    Activations Density 0.054%

    No Known Activations