© 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. 50221
    Prev
    Next
    INDEX
    Explanations

    ok, alright, OK, button

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

    The neuron strongly activates on code identifiers (class names, methods, parameters) used in UIAlertController/UIAlertAction API calls in Swift/Objective-C.

    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
     három
    -0.92
    gnac
    -0.88
    ïti
    -0.83
    beyaz
    -0.81
     CONSTANT
    -0.81
     hvit
    -0.81
    Kafka
    -0.79
     conteúdos
    -0.79
     ratón
    -0.77
     DOING
    -0.77
    POSITIVE LOGITS
     ok
    0.91
     порядке
    0.90
     OK
    0.83
     waved
    0.79
     terribly
    0.77
     נס
    0.76
     destructive
    0.75
     alright
    0.73
     urged
    0.72
     Hand
    0.72
    Activations Density 0.003%

    No Known Activations