© 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. 15840
    Prev
    Next
    INDEX
    Explanations

    code assignment keywords

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

    The neuron flags code tokens that combine or extend objects—especially calls to functions named “merge” or “extend.”

    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
     in
    -2.05
     if
    -1.80
     };
    -1.60
     finds
    -1.55
    </h1>
    -1.55
     It
    -1.52
     have
    -1.51
    );
    -1.51
     are
    -1.50
    她就
    -1.50
    POSITIVE LOGITS
     manto
    1.62
     gustos
    1.58
    Also
    1.58
    𝟏
    1.48
    他們
    1.48
    　　*
    1.43
     pantal
    1.40
    Already
    1.39
     balans
    1.38
    ه‌ی
    1.37
    Activations Density 0.003%

    No Known Activations