© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32693
    Prev
    Next
    INDEX
    Explanations

    leaders and officials

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

    The neuron fires on mentions of officials or executives being investigated, charged, or convicted for corruption—particularly bribery cases.

    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
    mögens
    -0.94
     Sociedad
    -0.84
    гинал
    -0.83
     Akshay
    -0.81
    нией
    -0.79
     základní
    -0.79
    ueras
    -0.78
    ickou
    -0.78
    ストラリア
    -0.77
     WING
    -0.77
    POSITIVE LOGITS
     leaders
    1.32
     secretary
    1.22
     cadres
    1.21
     Party
    1.16
     deputy
    1.14
    Cad
    1.13
     leadership
    1.13
     office
    1.13
     Leaders
    1.11
     Secretary
    1.09
    Activations Density 0.010%

    No Known Activations