© 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. 73915
    Prev
    Next
    INDEX
    Explanations

    delayed jobs or timed events

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

    The neuron is primarily detecting numeric literals (e.g. standalone numbers) 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
     τού
    -0.98
     préparer
    -0.85
     выска
    -0.81
    gyű
    -0.81
    Idk
    -0.80
     ವಿ
    -0.78
     çift
    -0.78
    bilden
    -0.76
    жений
    -0.76
     dépass
    -0.76
    POSITIVE LOGITS
     while
    0.97
    addEventListener
    0.93
     setInterval
    0.93
    ΤΑ
    0.92
     continuously
    0.91
    व
    0.88
    ͅ
    0.87
     periodically
    0.85
     pengelola
    0.85
    "]
    0.83
    Activations Density 0.025%

    No Known Activations