© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 10926
    Prev
    Next
    INDEX
    Explanations

    lists of names

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find commas that serve as separators in lists of names or items.

    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
     not
    -2.08
     facilitates
    -1.83
     at
    -1.80
     enables
    -1.73
     produces
    -1.69
     usually
    -1.69
     one
    -1.69
     as
    -1.68
     what
    -1.67
     might
    -1.67
    POSITIVE LOGITS
     horrid
    1.58
     momentan
    1.45
     actuellement
    1.44
     dreary
    1.44
     deliciously
    1.43
     intrigu
    1.43
    があり
    1.40
     hordes
    1.40
     mediocre
    1.38
     horrend
    1.38
    Activations Density 0.032%

    No Known Activations