© 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. 80909
    Prev
    Next
    INDEX
    Explanations

    followed by Sequential Events

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

    The neuron fires specifically on occurrences of the word “followed.”

    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
     both
    -0.93
    metrist
    -0.88
     完了
    -0.87
    冊
    -0.86
     indicada
    -0.84
    foreach
    -0.84
     salah
    -0.84
    と考えて
    -0.82
    Jvm
    -0.82
    FileUtil
    -0.82
    POSITIVE LOGITS
     by
    1.88
     followed
    1.55
     Followed
    1.45
     imme
    1.27
     closely
    1.22
     مباشرة
    1.18
     immediately
    1.16
     shortly
    1.10
    後に
    1.06
     Immediately
    1.06
    Activations Density 0.021%

    No Known Activations