© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41457
    Prev
    Next
    INDEX
    Explanations

    my way

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

    The neuron is primarily detecting occurrences of the word “way,” especially in phrases like “our way,” “your way,” or “my way.”

    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
     and
    -2.05
     each
    -1.94
    </em>
    -1.88
    It
    -1.73
    ) 
    -1.72
    which
    -1.69
     this
    -1.59
     Сегодня
    -1.59
    Since
    -1.54
     improve
    -1.53
    POSITIVE LOGITS
    蟥
    1.94
    
    1.91
     advierte
    1.91
    榇
    1.85
    毉
    1.84
    笵
    1.84
    赑
    1.84
    ౭
    1.83
     ferocious
    1.80
    
    1.76
    Activations Density 0.006%

    No Known Activations