© 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. 22-GEMMASCOPE-RES-131K
    7. 588
    Prev
    Next
    INDEX
    Explanations

    aspects of

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

    The neuron detects occurrences of the phrase “aspects of.”

    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
    梛
    -2.59
    ayage
    -2.52
    馘
    -2.48
    銫
    -2.31
     alugar
    -2.28
     comanda
    -2.23
     viață
    -2.22
    莇
    -2.20
     elección
    -2.17
    泅
    -2.16
    POSITIVE LOGITS
     of
    2.72
    3
    2.59
     voor
    2.56
     (
    2.48
     και
    2.45
     Для
    2.41
     für
    2.39
    t
    2.33
    et
    2.28
    f
    2.27
    Activations Density 0.009%

    No Known Activations