© 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. 25814
    Prev
    Next
    INDEX
    Explanations

    conjunction but

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

    This neuron is picking out discourse connectors—commas and coordinating conjunctions or sentence‐linking words.

    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
     então
    -0.79
    */].
    -0.78
     now
    -0.76
    每個
    -0.76
    なんと
    -0.75
     protože
    -0.73
    Га
    -0.73
    今では
    -0.72
    Pada
    -0.71
    又
    -0.71
    POSITIVE LOGITS
     make
    4.38
    Make
    3.63
    make
    3.55
     Make
    3.39
     MAKE
    2.78
    MAKE
    2.58
     makeup
    2.11
     делают
    1.60
    Makefile
    1.55
     hacen
    1.50
    Activations Density 0.041%

    No Known Activations