© 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. 22-GEMMASCOPE-RES-131K
    7. 14098
    Prev
    Next
    INDEX
    Explanations

    peace talks and negotiations

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

    The neuron detects terms related to diplomatic negotiations and formal peace or ceasefire agreements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     chré
    -1.35
    .
    -1.30
     are
    -1.29
    /
    -1.26
     of
    -1.24
     naturen
    -1.23
     zupełnie
    -1.16
    ➷
    -1.13
     الجلد
    -1.13
     spion
    -1.13
    POSITIVE LOGITS
    ebly
    1.49
     agreement
    1.48
     NSCoder
    1.44
    ensitive
    1.43
    ִּ
    1.40
    וּ
    1.34
     Affaires
    1.34
    🥽
    1.31
    廬
    1.31
    IKit
    1.29
    Activations Density 0.049%

    No Known Activations