© 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. 102033
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and real numbers

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

    The neuron detects tokens belonging to LaTeX blackboard‐bold commands or number‐set names (e.g. “mathbb,” “Z,” “R”).

    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
    pelo
    -1.41
     paltry
    -1.34
     betek
    -1.34
     It
    -1.32
    autés
    -1.24
    isateurs
    -1.24
     او
    -1.22
     succinctly
    -1.20
     وت
    -1.19
    cangan
    -1.16
    POSITIVE LOGITS
     этих
    1.55
    FOREWORD
    1.41
     about
    1.39
     azonban
    1.38
     indivíduo
    1.36
     however
    1.31
    噠
    1.29
     who
    1.26
    それぞれ
    1.26
    يي
    1.23
    Activations Density 0.023%

    No Known Activations