© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59713
    Prev
    Next
    INDEX
    Explanations

    half or ½

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

    The neuron strongly activates on numeric expressions—especially fractions, decimals, percentages, and other measurement values.

    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
    &
    -1.38
    -
    -1.38
    .
    -1.37
    volmente
    -1.32
     Institutionen
    -1.30
    Mask
    -1.27
    sept
    -1.26
     Pour
    -1.22
    ING
    -1.20
     Fernsehen
    -1.20
    POSITIVE LOGITS
    】：
    1.52
     çanta
    1.43
    ógica
    1.32
    ꯸
    1.31
    －－
    1.30
    ◾
    1.29
    徘
    1.29
     ayakkabı
    1.28
    谘
    1.28
     giyim
    1.26
    Activations Density 0.041%

    No Known Activations