© 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. 124743
    Prev
    Next
    INDEX
    Explanations

    overthrow, coup, or deposition

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

    This neuron detects tokens related to the forcible removal of political power (e.g., overthrow, coup, deposed, topple).

    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
    给我们
    -1.71
     *"
    -1.63
     Otros
    -1.62
    ™,
    -1.52
     sre
    -1.48
    between
    -1.48
     実例
    -1.48
     広場
    -1.48
     Muchos
    -1.44
    进入了
    -1.41
    POSITIVE LOGITS
     of
    2.05
    ↵
    1.80
    ing
    1.47
    也
    1.44
     создания
    1.39
     scoperto
    1.38
     inapropiados
    1.38
    坠
    1.37
    默默
    1.34
    它
    1.34
    Activations Density 0.021%

    No Known Activations