© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 12723
    Prev
    Next
    INDEX
    Explanations

    assignment or equality

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

    The neuron fires on programming code fragments—identifiers, operators, function/method names, assignments, and other syntax elements—rather than on ordinary prose.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _
    0.64
       
    0.58
     
    0.58
    ;
    0.57
     {
    0.56
     sleep
    0.56
     algorithm
    0.55
      
    0.54
     in
    0.54
     alttext
    0.53
    POSITIVE LOGITS
    +=
    0.72
     Assign
    0.71
    ]+=
    0.69
    assign
    0.69
    assignment
    0.68
     assigns
    0.68
    +="
    0.68
    Assign
    0.66
    赋值
    0.64
    ASSIGN
    0.64
    Activations Density 0.008%

    No Known Activations