© 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. 10-GEMMASCOPE-RES-131K
    4. 74977
    Prev
    Next
    INDEX
    Explanations

    then, followed by punctuation or question

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

    The neuron strongly activates on the discourse connective “then” (and related sequence‐marking punctuation), i.e. it detects the transitional word “then.”

    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
     fået
    -1.34
     bardzo
    -1.31
     trânsito
    -1.28
     vence
    -1.26
    帑
    -1.23
    چگونه
    -1.20
    ריים
    -1.20
    mga
    -1.18
    ケモン
    -1.18
     merece
    -1.17
    POSITIVE LOGITS
    “
    1.39
    it
    1.31
    1
    1.23
     "
    1.22
     or
    1.21
    is
    1.19
    "
    1.17
    id
    1.16
    list
    1.14
    choice
    1.12
    Activations Density 0.009%

    No Known Activations