© 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. 61450
    Prev
    Next
    INDEX
    Explanations

    ways to

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

    The neuron fires on words and phrases that introduce methods or approaches (e.g. “ways to…,” “in which…”)—in other words, it detects mentions of how something can be done.

    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
    
    -1.88
     blz
    -1.74
     elevador
    -1.64
     вернулся
    -1.60
     tomba
    -1.59
    
    -1.58
     手绘
    -1.56
    
    -1.55
    ampilkan
    -1.55
     ulei
    -1.55
    POSITIVE LOGITS
    </b>
    2.09
    u
    2.00
     -
    1.96
     '
    1.95
    s
    1.59
    )
    1.56
    at
    1.55
     "
    1.55
     :
    1.52
    es
    1.49
    Activations Density 0.046%

    No Known Activations