© 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. 105888
    Prev
    Next
    INDEX
    Explanations

    drink and what follows

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

    The neuron activates on any form of the word “drink” (e.g. “Drink,” “drink,” “DRINKER,” etc.).

    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
            
    -3.77
     вашу
    -3.28
        
    -3.17
    s
    -3.16
    </b>
    -3.08
     they
    -2.75
    4
    -2.64
     свою
    -2.61
     “
    -2.52
    All
    -2.48
    POSITIVE LOGITS
     decorada
    2.91
     санкт
    2.69
    鴣
    2.58
     solches
    2.50
    
    2.47
     знает
    2.47
    絝
    2.47
     夜景
    2.44
    鄖
    2.44
     壁纸
    2.28
    Activations Density 0.007%

    No Known Activations