© 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. 103721
    Prev
    Next
    INDEX
    Explanations

    code declarations and members

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

    This neuron fires on programming‐style identifiers and namespaces—particularly dotted package or class names and similar symbol tokens.

    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
    args
    -0.81
     材料
    -0.77
     Verlag
    -0.77
    椎
    -0.75
     args
    -0.75
     matrix
    -0.74
    参数
    -0.74
     supporter
    -0.73
    huana
    -0.73
     ternary
    -0.73
    POSITIVE LOGITS
     declaration
    0.85
     member
    0.83
    Symbol
    0.82
     mennes
    0.82
     members
    0.81
     Denkmal
    0.78
    स्थ
    0.77
    members
    0.76
     Declaration
    0.75
    declaration
    0.75
    Activations Density 0.029%

    No Known Activations