© 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. 77920
    Prev
    Next
    INDEX
    Explanations

    view pager

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find occurrences of the identifier “View” (and its compounds) in code.

    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
     MES
    -0.80
     francis
    -0.76
    いの
    -0.76
     Freem
    -0.73
    的东西
    -0.73
     percol
    -0.70
    AVE
    -0.69
     Wrestling
    -0.68
     Bou
    -0.68
    andowski
    -0.68
    POSITIVE LOGITS
    pager
    1.16
     group
    0.99
     findViewById
    0.98
    group
    0.92
    stub
    0.90
     għall
    0.85
    roup
    0.81
    𝙖
    0.81
    badger
    0.81
    findViewById
    0.80
    Activations Density 0.011%

    No Known Activations