© 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. 20458
    Prev
    Next
    INDEX
    Explanations

    forum or Q&A site terms

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

    The neuron fires on mentions of specific Stack Exchange communities or site‐related labels (e.g. “wiki”, “code-golf”, “Stack Exchange”).

    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
    </th>
    -1.51
    }{*}{
    -1.38
     of
    -1.35
    </h1>
    -1.33
    !
    -1.31
    )
    
    
    -1.24
    чите
    -1.23
    ">!
    -1.23
     {
    
    
    -1.23
    ]_{
    -1.23
    POSITIVE LOGITS
     then
    1.59
     néanmoins
    1.54
     complementar
    1.51
    
    1.40
     apropri
    1.36
     intermin
    1.36
     reutiliz
    1.36
     multiuso
    1.34
     elimina
    1.34
     vivía
    1.34
    Activations Density 0.098%

    No Known Activations