© 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. 11745
    Prev
    Next
    INDEX
    Explanations

    list items or enumerations

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

    This neuron detects list‐item enumeration markers (e.g. “ii)” or “2)”).

    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
     karier
    -1.69
     SIMILAR
    -1.68
     POSITIVE
    -1.55
     kader
    -1.54
     kredi
    -1.53
     SIMPLE
    -1.52
     maksi
    -1.51
     POSSIBLE
    -1.51
     ajouter
    -1.49
     katk
    -1.49
    POSITIVE LOGITS
     now
    1.91
     two
    1.85
     more
    1.84
     very
    1.80
     less
    1.77
     new
    1.77
    </
    1.74
    There
    1.70
     hampered
    1.67
     increased
    1.66
    Activations Density 0.105%

    No Known Activations