© 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. 10-GEMMASCOPE-RES-131K
    7. 101851
    Prev
    Next
    INDEX
    Explanations

    allows us to verb

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

    The neuron selectively activates on the word “us,” detecting that first-person plural objective pronoun.

    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
    癀
    -2.41
    鷸
    -2.02
    繍
    -1.99
    
    -1.98
    铪
    -1.98
     нього
    -1.91
    iſt
    -1.91
    勖
    -1.89
     {
    -1.88
     никогда
    -1.87
    POSITIVE LOGITS
     to
    3.84
     of
    3.36
     spezielle
    2.17
     It
    2.09
     jeweiligen
    2.06
     entsprechende
    2.06
     more
    2.00
     decisões
    1.97
     virtù
    1.88
    前来
    1.83
    Activations Density 0.011%

    No Known Activations