© 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. 98394
    Prev
    Next
    INDEX
    Explanations

    file paths

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

    The neuron fires on tokens naming filesystem directories or path components (e.g. “Documents”, “Desktop”, “Home”) in file paths.

    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
    Приготовление
    -1.17
    来週
    -1.15
    凄い
    -1.15
    Teknik
    -1.13
    ݯ
    -1.12
    為に
    -1.06
    Versión
    -1.06
     ochran
    -1.05
    ziem
    -1.04
     istilah
    -1.02
    POSITIVE LOGITS
    それも
    1.23
    でしょうね
    1.07
     ”
    1.05
    ₤
    1.05
    '%
    1.03
    ？」
    1.03
    decomposition
    1.00
    法則
    0.99
    ”
    0.98
    ichtete
    0.95
    Activations Density 0.032%

    No Known Activations