© 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. 22-GEMMASCOPE-RES-131K
    7. 129065
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on assignment/equality operators (the “=”) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    code snippets and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     kré
    -1.03
    [@"
    -0.97
    increased
    -0.96
     pájaro
    -0.94
     évé
    -0.93
     rése
    -0.93
     levé
    -0.92
     crucero
    -0.91
     rurales
    -0.90
    ("#{
    -0.90
    POSITIVE LOGITS
     if
    1.33
     bazı
    0.98
     оста
    0.98
     ícone
    0.93
     artefacts
    0.91
    Nils
    0.90
     corrig
    0.89
    最後は
    0.88
     complementar
    0.85
     eviden
    0.85
    Activations Density 0.001%

    No Known Activations