© 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. 63052
    Prev
    Next
    INDEX
    Explanations

    Russia, American, reduction, START, arms

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects discussion of geopolitical and military confrontation topics—especially U.S.–Russia relations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    émoc
    -0.78
     کاب
    -0.76
    ϳ
    -0.75
    ح
    -0.75
    ८
    -0.75
    voca
    -0.74
     Vichy
    -0.74
    ロット
    -0.73
    最终
    -0.73
    RAM
    -0.73
    POSITIVE LOGITS
     START
    1.20
     reductions
    1.16
     Russia
    1.16
     reduction
    0.96
     Russian
    0.95
     arms
    0.93
     SALT
    0.92
    START
    0.89
     reducing
    0.89
     reduce
    0.88
    Activations Density 0.014%

    No Known Activations