© 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. 22-GEMMASCOPE-RES-131K
    7. 14994
    Prev
    Next
    INDEX
    Explanations

    code comments and legal information

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

    The neuron strongly activates on words and phrases evoking violent conflict or warfare.

    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
     туры
    -2.03
     бампер
    -1.98
    嘴里
    -1.84
     อาหาร
    -1.84
    といふ
    -1.82
    多吃
    -1.81
     食物
    -1.76
     отды
    -1.73
    чает
    -1.69
    大な
    -1.68
    POSITIVE LOGITS
     with
    1.98
     before
    1.96
     five
    1.88
     државе
    1.78
     changed
    1.77
     Infir
    1.75
     clearly
    1.72
     pecuni
    1.68
    🪛
    1.66
     more
    1.66
    Activations Density 0.005%

    No Known Activations