© 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. 53937
    Prev
    Next
    INDEX
    Explanations

    because, since, reason conjunctions

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

    The neuron fires strongly on tokens that mark the beginnings (or ends) of major text blocks or sentences—essentially flagging paragraph or section boundaries.

    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
     this
    -1.37
     этого
    -1.27
     этом
    -1.06
     это
    -0.93
     mdl
    -0.92
     entonces
    -0.91
     этой
    -0.88
     then
    -0.88
     tampoco
    -0.87
    然后
    -0.85
    POSITIVE LOGITS
     because
    1.17
     Ведь
    1.12
    Ведь
    1.05
     क्योंकि
    1.05
     puisque
    0.97
     kerana
    0.96
     Çünkü
    0.95
     totiž
    0.94
     since
    0.94
     infatti
    0.94
    Activations Density 0.049%

    No Known Activations