© 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. 73702
    Prev
    Next
    INDEX
    Explanations

    additional updates

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

    The neuron primarily responds to numeric and quantitative information—numbers, dates, amounts, and related numeric tokens.

    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
    ACTO
    -0.88
    啻
    -0.85
    粼
    -0.85
    くらいで
    -0.85
     darbo
    -0.80
     támogat
    -0.77
     LoginComponent
    -0.77
     wären
    -0.77
     ဝ
    -0.77
    Retain
    -0.77
    POSITIVE LOGITS
     further
    1.76
     updated
    1.61
     additional
    1.55
    再度
    1.44
    additional
    1.43
    เพิ่มเติม
    1.42
    updated
    1.29
    再次
    1.27
     updates
    1.23
     ulteriori
    1.23
    Activations Density 0.085%

    No Known Activations