© 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. 115545
    Prev
    Next
    INDEX
    Explanations

    come followed by particle

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

    The neuron activates on the verb “come” in its various forms (come, comes, coming, came).

    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
    ILE
    -0.89
    КА
    -0.87
    宝宝
    -0.86
    minify
    -0.83
    商品の
    -0.81
    Ч
    -0.81
    Ν
    -0.81
    КУ
    -0.79
    ΑΣ
    -0.79
    чное
    -0.78
    POSITIVE LOGITS
     out
    1.35
     off
    1.05
     up
    1.00
    raph
    0.92
     down
    0.90
     through
    0.87
    wahati
    0.85
     isEnabled
    0.81
    mberto
    0.81
     alive
    0.80
    Activations Density 0.025%

    No Known Activations