© 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. 34-GEMMASCOPE-RES-131K
    7. 79305
    Prev
    Next
    INDEX
    Explanations

    code structure and international terms

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

    The neuron is detecting numeric literals (integer number tokens) 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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     even
    -1.18
     not
    -1.09
     although
    -1.02
     it
    -0.99
     Although
    -0.96
     in
    -0.90
     if
    -0.89
     oddly
    -0.88
     before
    -0.88
     as
    -0.87
    POSITIVE LOGITS
     {}
    1.32
     certamente
    1.16
    SOME
    1.04
     recentemente
    0.99
    {}
    0.99
     empleos
    0.98
     {})
    0.96
     {}
    0.96
    beleid
    0.96
    dienste
    0.94
    Activations Density 0.017%

    No Known Activations