© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27586
    Prev
    Next
    INDEX
    Explanations

    universal [noun]

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

    This neuron detects occurrences of the word “universal” (especially in title-case).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    腘
    -3.39
    댔
    -3.34
    mbgg
    -3.22
    訁
    -3.17
     dando
    -3.14
     wondrous
    -3.11
    ſſi
    -3.06
    
    -3.03
     sturdy
    -3.02
    wonderful
    -2.97
    POSITIVE LOGITS
     Surprisingly
    3.69
    there
    3.55
    There
    3.55
    Just
    3.45
    After
    3.38
     exquisitely
    3.33
    All
    3.31
    While
    3.27
    :
    3.25
     unparalleled
    3.20
    Activations Density 0.009%

    No Known Activations