© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67382
    Prev
    Next
    INDEX
    Explanations

    then, pois, depois

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

    This neuron fires on discourse-linking adverbs (like “depois,” “then,” “затем,” “pois”) that mark sequence or causal connection between clauses.

    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
    鰾
    -2.75
    蕺
    -2.66
    
    -2.58
    >");
    -2.56
    呖
    -2.53
    Ꮨ
    -2.52
    ⟞
    -2.45
    ){
    -2.45
    攆
    -2.44
    踅
    -2.39
    POSITIVE LOGITS
    {
    3.27
    This
    2.84
    The
    2.78
    in
    2.78
     However
    2.63
     Technically
    2.59
    It
    2.58
    甗
    2.50
                
    2.44
    当然
    2.39
    Activations Density 0.001%

    No Known Activations