© 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. 68966
    Prev
    Next
    INDEX
    Explanations

    plugging gaps and connecting

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

    The neuron fires on occurrences of the root “plug” (e.g., plug, plugs, plugged, plugging).

    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
    ïlande
    -2.17
    热的
    -1.89
    = 
    -1.85
     consummate
    -1.79
     habría
    -1.79
    ↵↵
    -1.79
    忉
    -1.76
     glance
    -1.73
    沣
    -1.71
    -1.70
    POSITIVE LOGITS
    紧接着
    2.27
    ではでは
    2.25
    ]
    2.13
    确实是
    2.06
    Alongside
    2.03
    \
    2.00
    其实是
    1.98
    饪
    1.97
     sambil
    1.96
    ついでに
    1.96
    Activations Density 0.005%

    No Known Activations