© 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. 104724
    Prev
    Next
    INDEX
    Explanations

    mathematical notation symbols

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

    The neuron strongly activates on numeric tokens (numbers or numerical substrings) in the text.

    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
     the
    -2.11
    圌
    -1.87
    ごちそうさまでした
    -1.85
    ご馳走
    -1.57
    馬鹿
    -1.55
    それにしても
    -1.53
    どうやら
    -1.53
     CREAT
    -1.53
     remercier
    -1.50
    if
    -1.48
    POSITIVE LOGITS
     With
    1.89
     bonté
    1.79
     with
    1.72
    艽
    1.61
    InputBorder
    1.61
    mètres
    1.59
    儈
    1.59
    ācijas
    1.58
    AsUp
    1.57
     Ironically
    1.56
    Activations Density 0.057%

    No Known Activations