© 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. 34-GEMMASCOPE-RES-131K
    7. 103587
    Prev
    Next
    INDEX
    Explanations

    Aurora, Aurelian, auranofin

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

    the name "Aurelius" or its variants like "Aurelian", "Aurelia", "Aurungzebe" or "Aurin".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on tokens containing the substring “aur” (e.g. portions of words like “Aurelien,” “aurochs,” or “aurintricarboxylic”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     пошли
    -0.90
    haël
    -0.88
     Hormone
    -0.85
    ῦ
    -0.79
    ferential
    -0.79
    ร์
    -0.79
     Emergence
    -0.77
    ctuary
    -0.76
     salam
    -0.75
    屾
    -0.73
    POSITIVE LOGITS
     borealis
    0.91
    Aurora
    0.82
     drain
    0.81
     Aur
    0.80
    Aur
    0.79
     EXT
    0.71
    mimetype
    0.71
    apura
    0.70
    Sept
    0.69
     Aurora
    0.69
    Activations Density 0.015%

    No Known Activations