© 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. 70343
    Prev
    Next
    INDEX
    Explanations

    Objective-C initialization methods

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

    The neuron fires on Objective-C initializer method names, especially occurrences of “initWith…” in 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_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
     flatten
    -0.74
    azol
    -0.72
     religion
    -0.72
    kungen
    -0.70
     getToken
    -0.69
     addition
    -0.68
    ieš
    -0.68
     Ankunft
    -0.68
    变得
    -0.67
     čin
    -0.67
    POSITIVE LOGITS
     nib
    1.06
    Coder
    1.06
    nib
    1.04
     style
    1.00
     styles
    0.91
    Nib
    0.89
    coder
    0.89
     estilos
    0.87
     frame
    0.84
     Econ
    0.81
    Activations Density 0.021%

    No Known Activations