© 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. 10986
    Prev
    Next
    INDEX
    Explanations

    division by numbers

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

    The main thing this neuron does is detect numeric division expressions (fractions) written with a slash.

    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
     they
    -1.41
     خواهید
    -1.29
    他们
    -1.21
    もあって
    -1.08
    などは
    -1.08
     nyel
    -1.08
     thuy
    -1.06
    惱
    -1.06
    なども
    -1.05
    Ր
    -1.05
    POSITIVE LOGITS
     it
    1.12
     mehreren
    1.11
    ＝＝＝＝
    1.07
    liwości
    1.07
    に戻
    1.06
     تانيه
    1.05
     größte
    1.05
    のですか
    1.05
    に戻る
    1.04
    螢
    1.02
    Activations Density 0.004%

    No Known Activations