© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7257
    Prev
    Next
    INDEX
    Explanations

    object keys or identifiers

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

    The neuron activates on code-style parameter or property names (e.g. configuration keys) in technical text.

    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
    它們
    0.74
    °-
    0.72
    它们
    0.69
     nende
    0.68
     INNOV
    0.67
    -]
    0.66
    ׄ
    0.66
    )>\
    0.65
     EARL
    0.64
     لیګ
    0.64
    POSITIVE LOGITS
    :
    1.05
    :'',
    1.04
    :{
    0.99
    :[
    0.96
    (){
    0.94
    :"",
    0.94
    :(
    0.88
    ":{"
    0.83
     :
    0.82
    ':[
    0.81
    Activations Density 0.001%

    No Known Activations