© 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. 22-GEMMASCOPE-RES-131K
    7. 36186
    Prev
    Next
    INDEX
    Explanations

    international code snippets and programming terms

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

    The neuron detects code tokens related to loading or retrieving images (e.g. UIImage imageNamed, contentsOfURL, resource identifiers) in iOS 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_22/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
    Quiénes
    -1.28
     يب
    -1.21
    ējās
    -1.19
     become
    -1.14
     who
    -1.13
    tifiable
    -1.13
    ونده
    -1.09
     becoming
    -1.05
    vraagd
    -1.02
    e
    -1.02
    POSITIVE LOGITS
    今も
    1.23
     بدون
    1.21
     Communicating
    1.19
     demikian
    1.18
    Sadly
    1.16
    
    1.16
    améli
    1.16
     intérieure
    1.13
    ıdır
    1.13
     actuellement
    1.13
    Activations Density 0.002%

    No Known Activations