© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80858
    Prev
    Next
    INDEX
    Explanations

    violent clashes and conflict

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

    The neuron activates most strongly on words describing armed hostilities or combat (e.g. “fighting,” “clashes,” “heavy fighting”).

    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
    zuführen
    -0.82
     cylinders
    -0.75
    終了
    -0.75
     PEST
    -0.74
     hyal
    -0.73
    ियाँ
    -0.72
     isoforms
    -0.72
     беше
    -0.72
     rant
    -0.71
    fstream
    -0.71
    POSITIVE LOGITS
     clashes
    2.92
     clash
    2.31
     clashed
    2.03
     fighting
    1.76
     violence
    1.74
     Clash
    1.61
     conflict
    1.55
     battles
    1.54
     skir
    1.54
    clash
    1.51
    Activations Density 0.042%

    No Known Activations