© 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. 82396
    Prev
    Next
    INDEX
    Explanations

    special envoy or assistant

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

    The neuron strongly activates on tokens that are part of formal titles, offices, or official positions (e.g. “presidents,” “appointed,” “special adviser,” “rapporteur,” “Representative,” “plenipotentiary,” etc.).

    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
    銚
    -0.80
    PRESIDENT
    -0.80
     رئیس
    -0.74
    とろ
    -0.73
    default
    -0.71
    racuse
    -0.70
     doped
    -0.68
    Versatile
    -0.68
    𝙾
    -0.68
     Presidente
    -0.67
    POSITIVE LOGITS
     envoy
    1.90
     special
    1.65
    envoy
    1.51
     Envoy
    1.45
    Special
    1.41
     Special
    1.41
     enviado
    1.32
    special
    1.31
     специаль
    1.31
     envoyé
    1.29
    Activations Density 0.038%

    No Known Activations