© 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. 22-GEMMASCOPE-RES-131K
    7. 12601
    Prev
    Next
    INDEX
    Explanations

    riot and violent protests

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

    The neuron detects words and phrases associated with protests, demonstrations, and crowd-control or riot situations.

    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
     sogni
    -1.37
    bigoplus
    -1.26
    #@
    -1.26
    emples
    -1.23
     (
    -1.23
    вей
    -1.20
     years
    -1.18
    $
    -1.16
     studies
    -1.14
    foreach
    -1.14
    POSITIVE LOGITS
    Сылтамалар
    1.35
     cikk
    1.30
    fokus
    1.25
    keyColumn
    1.24
    ִּ
    1.23
    ಆ
    1.23
     órdenes
    1.23
     Wednesday
    1.21
    unakan
    1.20
     mężczyzn
    1.19
    Activations Density 0.040%

    No Known Activations