© 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. 22-GEMMASCOPE-RES-131K
    7. 11102
    Prev
    Next
    INDEX
    Explanations

    code structure symbols

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

    The neuron activates on capitalized, PascalCase identifiers (e.g. class, constructor, or method names) in source 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_22/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
    AuthGuard
    -1.05
    派遣
    -0.93
    kuwa
    -0.93
     perder
    -0.92
     the
    -0.91
    gesetzt
    -0.89
    研究
    -0.88
     trit
    -0.88
     también
    -0.87
     it
    -0.87
    POSITIVE LOGITS
     Nausea
    1.00
     data
    0.99
    致します
    0.96
    ◢
    0.96
    するか
    0.96
     activities
    0.93
     liderazgo
    0.92
    Kedua
    0.91
     христи
    0.91
     inapropiados
    0.91
    Activations Density 0.036%

    No Known Activations