© 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. 103949
    Prev
    Next
    INDEX
    Explanations

    a/an followed by a specific noun

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

    The neuron primarily detects numeric tokens (especially decimal numbers) representing measurements or values in the text.

    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
    excellents
    -1.70
     out
    -1.59
    abbaye
    -1.59
    famous
    -1.57
     antwoord
    -1.55
     it
    -1.51
     examples
    -1.48
     verschiedenen
    -1.48
     helicópter
    -1.45
     bestaande
    -1.41
    POSITIVE LOGITS
    циями
    1.48
     EXPERIMENTS
    1.48
    对于
    1.46
     cuillère
    1.46
    在我
    1.45
    tedy
    1.45
     بنابراین
    1.43
     erne
    1.41
    對於
    1.38
     évidence
    1.37
    Activations Density 0.073%

    No Known Activations