© 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. 68930
    Prev
    Next
    INDEX
    Explanations

    contour

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

    The neuron is highly sensitive to occurrences of the term “contour” (and its variants) in the text.

    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
    簠
    -3.14
    gucig
    -3.11
    呶
    -2.95
    甞
    -2.95
     prenotazione
    -2.86
    
    -2.77
    謦
    -2.72
    ᷆
    -2.72
    缯
    -2.72
    鬭
    -2.70
    POSITIVE LOGITS
    —
    3.31
    <em>
    3.30
    “
    2.92
    、“
    2.88
    ↵
    2.55
      
    2.55
     consequently
    2.52
    to
    2.50
     of
    2.50
    芣
    2.48
    Activations Density 0.001%

    No Known Activations