© 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. 22601
    Prev
    Next
    INDEX
    Explanations

    application structure and components

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

    The neuron primarily activates on mentions of “MainWindow” (or “main window”) identifiers, i.e. references to the application’s main 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
     :
    -2.86
    大多
    -2.64
     unſ
    -2.48
    ,(
    -2.47
    烀
    -2.45
     gebeten
    -2.44
     gewiß
    -2.41
    ?"
    -2.30
     They
    -2.30
    }$
    -2.28
    POSITIVE LOGITS
    𓆜
    3.02
    鱘
    2.86
    驁
    2.81
     échelle
    2.81
    饗
    2.80
    。】
    2.72
     iluminación
    2.64
    嵛
    2.63
    有難
    2.58
    齎
    2.58
    Activations Density 0.001%

    No Known Activations