© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1497
    Prev
    Next
    INDEX
    Explanations

    android onCreate methods

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

    The neuron strongly activates on numeric tokens (integer literals or numbers) 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
     remained
    -0.81
     forState
    -0.81
     only
    -0.80
     appears
    -0.78
    でしたか
    -0.75
    expect
    -0.74
    Причины
    -0.73
     expect
    -0.70
     causing
    -0.69
    üssel
    -0.69
    POSITIVE LOGITS
     on
    1.57
    onCreate
    1.36
     onCreate
    1.27
     dispatch
    0.96
     על
    0.95
    CREATED
    0.93
     созда
    0.93
     Dispatch
    0.92
    Dispatch
    0.90
    onRequest
    0.88
    Activations Density 0.023%

    No Known Activations