© 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. 10-GEMMASCOPE-RES-131K
    7. 105094
    Prev
    Next
    INDEX
    Explanations

    riots and unrest

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

    This neuron responds to mentions of riots or similar violent mass protests.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    </h2>
    -2.61
    as
    -2.44
    ſſer
    -2.41
    閙
    -2.34
    lossians
    -2.33
    ⽤
    -2.23
    after
    -2.22
    mallera
    -2.20
    Ⲉ
    -2.20
     моя
    -2.19
    POSITIVE LOGITS
    }
    3.75
    .
    3.13
    ↵
    2.69
    ೣ
    2.28
    mathrm
    2.27
    {
    2.25
     caminh
    2.20
     nimmer
    2.17
     momentan
    2.17
     lança
    2.09
    Activations Density 0.002%

    No Known Activations