© 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. 69099
    Prev
    Next
    INDEX
    Explanations

    doing things

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

    The neuron fires on generic “activity” terms—especially the noun “things” and various forms of the verb “do.”

    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
    iſter
    -1.95
     naudoti
    -1.80
     некоторы
    -1.71
     pudieron
    -1.62
     dénon
    -1.57
     ayudó
    -1.57
     knihy
    -1.56
     respald
    -1.55
     querían
    -1.55
    ované
    -1.54
    POSITIVE LOGITS
     about
    1.78
    $
    1.71
    >
    1.70
    te
    1.62
    ↵↵
    1.60
     like
    1.52
     为
    1.48
    ти
    1.43
     by
    1.39
     he
    1.38
    Activations Density 0.093%

    No Known Activations