© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 87002
    Prev
    Next
    INDEX
    Explanations

    row and index paths

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

    The neuron fires on code references to indexPath (e.g. methods like cellForRowAtIndexPath, numberOfRowsInSection, didSelectItemAtIndexPath, and bracketed indexPath array accesses).

    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
    pagesize
    -0.77
    絲
    -0.75
     Sorbonne
    -0.71
    丝
    -0.71
    endtime
    -0.69
    viser
    -0.69
    NavigationView
    -0.68
     baca
    -0.68
     Lena
    -0.68
    Lena
    -0.67
    POSITIVE LOGITS
     row
    1.55
    indexPath
    1.52
    NSIndexPath
    1.43
     indexPath
    1.42
    IndexPath
    1.38
    row
    1.30
    Row
    1.22
     IndexPath
    1.18
     Row
    1.16
    path
    1.02
    Activations Density 0.053%

    No Known Activations