© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12714
    Prev
    Next
    INDEX
    Explanations

    universal themes and archetypes

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

    The neuron activates on occurrences of the word “universal” (and its variants like “universally” or related forms).

    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
     into
    -1.38
     etc
    -1.34
     儿
    -1.31
    ErrUnexpectedEOF
    -1.29
     For
    -1.25
     η
    -1.25
    などに
    -1.23
     is
    -1.17
                   
    -1.17
                  
    -1.16
    POSITIVE LOGITS
     then
    1.29
     нужен
    1.23
    J
    1.23
     <",
    1.21
    ⑴
    1.20
    tragung
    1.16
     nochmals
    1.16
     questions
    1.12
    ➊
    1.09
    you
    1.09
    Activations Density 0.056%

    No Known Activations