© 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. 68750
    Prev
    Next
    INDEX
    Explanations

    code and xml constructs

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

    The neuron is triggered by standalone numeric literals (e.g. numbers like 115, 113, 109) in code.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     of
    -2.14
                
    -1.98
     in
    -1.75
    н
    -1.74
     and
    -1.72
     dubbed
    -1.72
    ühnen
    -1.66
     This
    -1.59
    "
    -1.58
    のおかげ
    -1.55
    POSITIVE LOGITS
    휀
    2.31
    应该
    2.17
     Haushalt
    2.14
    ﮩ
    1.99
     つの
    1.91
    
    1.91
     Aufwand
    1.91
     любой
    1.90
    出一个
    1.88
    這些
    1.87
    Activations Density 0.020%

    No Known Activations