© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 1227
    Prev
    Next
    INDEX
    Explanations

    boxing primitive types

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

    The neuron specifically flags Objective-C symbols and literal constructs (e.g. CF*/NS* class names, @‐prefixed literals, NO, NSNull, dictionary‐literal syntax).

    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
    wiad
    -0.82
    dsquared
    -0.78
    lds
    -0.78
    TRIBUT
    -0.77
    ως
    -0.74
    ords
    -0.74
    CharSequence
    -0.74
    stars
    -0.73
    ield
    -0.72
    utor
    -0.72
    POSITIVE LOGITS
     boxed
    1.13
    boxed
    1.09
     box
    0.95
    valueOf
    0.94
     valueOf
    0.90
     Integer
    0.87
     tedy
    0.86
    NSNumber
    0.85
     Box
    0.84
     boxing
    0.83
    Activations Density 0.004%

    No Known Activations