© 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. 73605
    Prev
    Next
    INDEX
    Explanations

    Black Lives Matter and movements

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

    The neuron responds to names, slogans, and key terms of social and political movements (e.g. Black Lives Matter, BLM, #MeToo, boycott/divestment/sanctions, Occupy, etc.).

    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
    Nr
    -0.79
     implemented
    -0.77
    rischen
    -0.76
    تماد
    -0.76
    Toxicity
    -0.75
    加工
    -0.74
    wydd
    -0.72
     rite
    -0.72
     muco
    -0.70
    tismo
    -0.69
    POSITIVE LOGITS
     BLM
    1.95
    BLM
    1.54
     Black
    1.49
    Black
    1.41
     حركة
    1.01
     movement
    1.00
     Lives
    0.94
     BLACK
    0.93
    black
    0.93
    movement
    0.92
    Activations Density 0.012%

    No Known Activations