© 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. 70570
    Prev
    Next
    INDEX
    Explanations

    .self

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

    The neuron activates on numeric literals (numbers and numeric constants) 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
     permitiendo
    -0.96
     ifølge
    -0.87
    miu
    -0.87
     Übung
    -0.85
     einschließlich
    -0.84
    ture
    -0.81
     május
    -0.81
    
    -0.81
    формация
    -0.81
     ILLUSTRATIONS
    -0.80
    POSITIVE LOGITS
    添加到
    1.00
    Istorija
    0.90
     Herzog
    0.87
    氪
    0.87
    ỗng
    0.87
     grafting
    0.85
     父
    0.85
    ām
    0.85
    belum
    0.84
    schw
    0.83
    Activations Density 0.007%

    No Known Activations