© 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. 10-GEMMASCOPE-RES-131K
    7. 102466
    Prev
    Next
    INDEX
    Explanations

    peace and conflict

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

    The neuron fires on occurrences of the word “peace” (and closely related peace‐themed terms) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     desarrollar
    -1.34
    杞
    -1.32
     hornear
    -1.32
     stands
    -1.30
     sàng
    -1.30
     reveló
    -1.23
     買取
    -1.20
     zarówno
    -1.20
     possessed
    -1.19
    baomidou
    -1.18
    POSITIVE LOGITS
     cinquième
    1.52
    ቼ
    1.52
     quatrième
    1.47
    2
    1.39
    ämpfer
    1.34
    R
    1.31
     Konkur
    1.28
     konsek
    1.27
     它
    1.27
     troisième
    1.24
    Activations Density 0.029%

    No Known Activations