© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22621
    Prev
    Next
    INDEX
    Explanations

    window creation and manipulation

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

    The neuron activates on code tokens referring to window‐related constructs or API calls (i.e. mentions of “Window”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    
    -3.23
    埽
    -3.09
    硨
    -2.97
    er
    -2.95
     humeur
    -2.83
    鲥
    -2.75
     botol
    -2.63
    出す
    -2.59
     sabun
    -2.56
     itſelf
    -2.53
    POSITIVE LOGITS
    ?
    2.97
    -
    2.94
     ``
    2.77
      
    2.73
     SOME
    2.70
    ↵↵
    2.69
    ではまた
    2.58
    唠
    2.48
    とはいえ
    2.42
    =
    2.36
    Activations Density 0.002%

    No Known Activations