© 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. 34-GEMMASCOPE-RES-131K
    7. 119227
    Prev
    Next
    INDEX
    Explanations

    ordered or disordered collections

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

    The neuron activates on any token containing the “order”/“sort” root—i.e. words referring to ordering or sorting (e.g. ordered, Sorted, unordered, OrderedDict).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ker
    -0.84
     fx
    -0.84
    lder
    -0.81
     좋은
    -0.81
    决定
    -0.80
    ghs
    -0.80
     recto
    -0.79
    GETHER
    -0.78
     émotions
    -0.78
    hu
    -0.77
    POSITIVE LOGITS
     list
    1.13
     collection
    0.91
     collections
    0.89
     lists
    0.81
     unique
    0.75
     dependable
    0.75
    残酷
    0.74
     vaginal
    0.73
     interestingly
    0.73
    nī
    0.71
    Activations Density 0.041%

    No Known Activations