© 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. 54151
    Prev
    Next
    INDEX
    Explanations

    loader instantiation

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

    The neuron fires on occurrences of the identifier “Loader” (or tokens containing “Loader”) 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
     Carver
    -0.78
     Lawson
    -0.76
    📫
    -0.75
    agos
    -0.74
     sprawling
    -0.73
    र्ड
    -0.73
    𝐎
    -0.73
     ISA
    -0.73
    𝚎
    -0.73
     Mile
    -0.71
    POSITIVE LOGITS
     Loader
    1.26
     loader
    1.23
     onLoad
    1.09
    Loader
    1.01
     loaders
    0.94
    OnLoad
    0.89
     load
    0.85
    loader
    0.84
    oader
    0.79
    Callbacks
    0.78
    Activations Density 0.005%

    No Known Activations