© 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. 28369
    Prev
    Next
    INDEX
    Explanations

    introduces specific elaboration

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

    The neuron is keyed to discourse-level transition words or adverbial connectives (e.g. “Indeed,” “Namely,” “In fact”) that signal a logical or emphatic shift in the text.

    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
     and
    -1.81
     también
    -1.45
     także
    -1.27
    ==""){
    -1.23
     также
    -1.16
     cependant
    -1.14
    捋
    -1.13
    andowski
    -1.12
    //}
    -1.12
     também
    -1.12
    POSITIVE LOGITS
     unlike
    1.43
     when
    1.33
     lately
    1.32
     since
    1.28
     recently
    1.27
     whereas
    1.24
    Whilst
    1.20
     whilst
    1.20
     nowadays
    1.18
     lorsque
    1.17
    Activations Density 0.019%

    No Known Activations