© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 10856
    Prev
    Next
    INDEX
    Explanations

    code identifiers and delimiters

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

    This neuron detects programming identifiers (variable and function names) 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_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
    cazione
    -1.00
     to
    -0.95
     recoil
    -0.93
    Accel
    -0.91
    яд
    -0.90
    mannen
    -0.90
     of
    -0.89
    nO
    -0.88
    malıdır
    -0.87
    レクト
    -0.86
    POSITIVE LOGITS
     GRATU
    1.05
     démission
    1.02
     companyId
    1.01
    中島
    0.98
     createdBy
    0.98
     courseId
    0.97
    ――――
    0.96
    中村
    0.96
     Monographs
    0.93
     usługi
    0.92
    Activations Density 0.006%

    No Known Activations