© 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. 101793
    Prev
    Next
    INDEX
    Explanations

    the verb affect

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

    The neuron strongly activates on occurrences of the verb “affect.”

    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
    蜴
    -2.67
    是被
    -2.50
    篥
    -2.44
    liwości
    -2.42
    姈
    -2.41
    是很
    -2.34
    i
    -2.33
    
    -2.33
     аккура
    -2.33
     邸
    -2.33
    POSITIVE LOGITS
    {
    2.98
    t
    2.92
    ↵
    2.31
     you
    2.11
     stupidly
    2.08
    ING
    2.05
     affect
    2.02
     dozen
    2.00
    子供が
    2.00
     Там
    1.96
    Activations Density 0.009%

    No Known Activations