© 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. 75223
    Prev
    Next
    INDEX
    Explanations

    on followed by verb or noun

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

    The main thing this neuron does is detect occurrences of the substring “on” in callback or lifecycle method names.

    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
    蟥
    -1.95
     唯美
    -1.92
    supposed
    -1.87
    presumably
    -1.87
    apparently
    -1.84
    truly
    -1.77
     constitue
    -1.75
    seems
    -1.75
     adesivo
    -1.75
    蚰
    -1.73
    POSITIVE LOGITS
    L
    1.86
     from
    1.74
     like
    1.74
     after
    1.73
    After
    1.73
    A
    1.68
    Some
    1.66
    just
    1.66
     h
    1.65
    One
    1.65
    Activations Density 0.003%

    No Known Activations