© 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. 64240
    Prev
    Next
    INDEX
    Explanations

    code structure markers

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

    The neuron activates on standalone numeric literals (numbers) in code or text.

    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
    [:,:,
    -1.08
     ()=>{
    -1.06
     
    -1.03
    (""+
    -0.95
    ={()=>
    -0.91
    ="<?=$
    -0.88
     ()=>
    -0.86
     brugt
    -0.85
     venn
    -0.82
     pinterest
    -0.81
    POSITIVE LOGITS
    (""
    0.84
     به‌
    0.84
     však
    0.82
    ."""
    0.78
    //}
    0.76
     alas
    0.75
     coined
    0.74
    azawa
    0.74
     enqu
    0.73
    omány
    0.73
    Activations Density 0.366%

    No Known Activations