© 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. 34-GEMMASCOPE-RES-131K
    7. 63005
    Prev
    Next
    INDEX
    Explanations

    code symbols and syntax

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

    The neuron strongly activates on programming‐ and code‐related header terms (like “source,” “code,” and “symbol”).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     bereits
    -0.91
    天子
    -0.87
     their
    -0.81
    ("]");
    -0.81
    出来了
    -0.81
     Repr
    -0.77
     brings
    -0.76
     several
    -0.75
     вже
    -0.75
     dominates
    -0.74
    POSITIVE LOGITS
     is
    1.16
     ausein
    0.96
    神经
    0.92
    meaning
    0.90
    wochen
    0.87
    hift
    0.86
    tritt
    0.84
    though
    0.84
    ——
    0.83
     ieder
    0.82
    Activations Density 0.001%

    No Known Activations