© 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. 10-GEMMASCOPE-RES-131K
    7. 70556
    Prev
    Next
    INDEX
    Explanations

    catheterization, cstdio, Celine Dion

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

    The neuron activates on C/C++ include directives for the <cstdio> header.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    素晴らしい
    -2.64
    P
    -2.52
    ный
    -2.45
    釓
    -2.45
    ‌ها
    -2.42
    ge
    -2.42
    F
    -2.41
    "
    -2.39
    的
    -2.38
    杁
    -2.36
    POSITIVE LOGITS
     größte
    2.69
    紲
    2.67
     Einfluß
    2.67
     verbess
    2.64
    注意事
    2.56
     übri
    2.50
     letzte
    2.47
     wichtigste
    2.42
     unangemessene
    2.42
    .’
    2.42
    Activations Density 0.032%

    No Known Activations