© 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. 75549
    Prev
    Next
    INDEX
    Explanations

    competition contexts and clauses

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

    The neuron consistently responds to mentions of the concept of competition, activating on the word “competition” (in any capitalization) 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
    同伴
    -2.86
    邂
    -2.64
    N
    -2.61
     ‘
    -2.61
     применя
    -2.59
    ！"
    -2.56
     Your
    -2.53
    This
    -2.52
    ꦗ
    -2.45
    眼下
    -2.44
    POSITIVE LOGITS
    ↵
    3.36
     parachoque
    3.22
    łku
    3.00
    屜
    2.95
    淠
    2.81
    ～。
    2.80
    ”،
    2.70
    階段
    2.59
    轫
    2.56
     nhưng
    2.52
    Activations Density 0.014%

    No Known Activations