© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99031
    Prev
    Next
    INDEX
    Explanations

    code keywords and structure

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

    The neuron activates on numeric literal tokens (integers and floating‐point numbers) in code.

    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
    нусы
    -1.41
     to
    -1.31
    lovely
    -1.30
     हैं
    -1.30
    𝘦
    -1.30
    </u>
    -1.27
     يول
    -1.27
     сталь
    -1.24
    tyfik
    -1.24
     și
    -1.23
    POSITIVE LOGITS
     возможность
    1.80
    This
    1.77
     possibility
    1.53
     need
    1.48
     japonés
    1.46
    狁
    1.38
     見る
    1.32
     plainly
    1.32
    
    1.30
     hôm
    1.29
    Activations Density 0.080%

    No Known Activations