© 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. 84029
    Prev
    Next
    INDEX
    Explanations

    protest and demonstrations

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

    The neuron is strongly activated by words referring to protests or demonstrations (e.g. protest, protests, protester, march).

    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
     riot
    -0.94
     barrica
    -0.90
     barricade
    -0.90
     picnic
    -0.86
     essentials
    -0.83
    Snack
    -0.80
    策略
    -0.79
    Riot
    -0.77
     bonos
    -0.75
     leaders
    -0.75
    POSITIVE LOGITS
     protests
    2.30
     protest
    1.71
     protested
    1.70
     protestas
    1.45
     Protest
    1.23
     protesting
    1.23
    protest
    1.18
     prosthesis
    1.16
     protesta
    1.12
     protes
    1.09
    Activations Density 0.038%

    No Known Activations