© 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. 105710
    Prev
    Next
    INDEX
    Explanations

    programming class definitions

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

    the word "class" in programming and technical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on occurrences of the word “class” (especially in code or technical contexts).

    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
     guerrero
    -1.71
     kafe
    -1.67
     boute
    -1.64
     pè
    -1.63
     vixion
    -1.63
    くらいで
    -1.59
     bisous
    -1.58
     Gouvernement
    -1.58
     elever
    -1.58
     talle
    -1.57
    POSITIVE LOGITS
    ");
    1.73
    ];
    1.68
    '];
    1.66
    }{
    1.59
    ]){
    1.51
    </sup>
    1.49
    </h2>
    1.48
    >();
    1.46
    );
    
    
    1.42
    ){
    1.41
    Activations Density 0.000%

    No Known Activations