© 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. 63861
    Prev
    Next
    INDEX
    Explanations

    peace and associated concepts

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

    The neuron fires strongly on occurrences of the token “peace” (especially capitalized), for example in titles or proper‐name contexts.

    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
    籏
    -0.96
     successes
    -0.94
     dreary
    -0.88
     recognize
    -0.87
     incredibly
    -0.85
     closely
    -0.84
    gewiesen
    -0.83
    nadier
    -0.81
     momentous
    -0.81
     decides
    -0.78
    POSITIVE LOGITS
    FUL
    1.52
    fulness
    1.36
    Peace
    1.28
     Peace
    1.26
     peace
    1.20
    maker
    1.16
    makers
    1.08
    keepers
    1.05
    able
    1.05
    ful
    1.04
    Activations Density 0.008%

    No Known Activations