© 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. 75529
    Prev
    Next
    INDEX
    Explanations

    Circus or Blender

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

    The neuron fires strongly on mentions of “circus” (and its variants like “Circo”) or references to a circus-style sideshow.

    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
    谞
    -2.98
    玏
    -2.72
    菔
    -2.70
    .''
    -2.59
    佧
    -2.48
    饪
    -2.45
    釔
    -2.44
     leaſt
    -2.38
    ではでは
    -2.36
    妘
    -2.36
    POSITIVE LOGITS
    ↵↵
    2.84
    ’
    2.47
    "
    2.47
      
    2.23
    .
    2.19
    蹰
    2.19
     аспек
    2.14
    JTextField
    2.06
     umgekehrt
    2.06
    说
    2.05
    Activations Density 0.003%

    No Known Activations