© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38824
    Prev
    Next
    INDEX
    Explanations

    foreign language programming terms

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

    The neuron detects tokens that are part of method or function parameter lists (i.e. parameter names, their types, and the surrounding punctuation).

    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
    畝
    -1.05
     امیر
    -0.97
    Jeho
    -0.96
    LOUIS
    -0.96
    Nek
    -0.96
     اصفه
    -0.95
    蟄
    -0.94
    INNOV
    -0.93
    IMDb
    -0.93
    Vivi
    -0.92
    POSITIVE LOGITS
     وال
    0.93
    浙江
    0.90
    Dě
    0.90
     gaat
    0.88
     Antrag
    0.87
    Mű
    0.85
     quiera
    0.84
     dimentic
    0.83
     Kindes
    0.83
     Symptome
    0.82
    Activations Density 0.003%

    No Known Activations