© 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. 66067
    Prev
    Next
    INDEX
    Explanations

    algorithms and sorting

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

    The neuron fires whenever the text refers to sorting algorithms or includes the sorting library (e.g. “algorithm,” “sort,” “sorted”).

    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
    quartered
    -1.74
    givers
    -1.60
    粢
    -1.59
    亍
    -1.57
    panes
    -1.55
    outWeight
    -1.55
    Ⅰ
    -1.53
    moor
    -1.52
    entown
    -1.51
    BIE
    -1.50
    POSITIVE LOGITS
     it
    1.97
     one
    1.87
     with
    1.66
     on
    1.64
     into
    1.61
     during
    1.48
     this
    1.48
     through
    1.45
     people
    1.44
     though
    1.42
    Activations Density 0.027%

    No Known Activations