© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113636
    Prev
    Next
    INDEX
    Explanations

    Swift/Objective-C initializers

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

    initializer declarations (init methods) in Swift code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is triggered by Swift initializer (“init”) definitions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    '
    -2.42
    :+:
    -1.64
     ultima
    -1.59
    AtIndexPath
    -1.52
    ؟
    -1.52
    Ḿ
    -1.51
    偲
    -1.48
    IVENESS
    -1.46
     Both
    -1.45
    häuser
    -1.45
    POSITIVE LOGITS
    摃
    2.06
     kleineren
    2.02
     vielen
    1.86
     zahlreichen
    1.84
     kleinen
    1.77
    ientras
    1.74
     hebben
    1.71
     forbindelse
    1.65
    guigu
    1.65
     pervasive
    1.59
    Activations Density 0.001%

    No Known Activations