© 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. 57482
    Prev
    Next
    INDEX
    Explanations

    Category names and code snippets

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

    This neuron responds to HTML table cell tags (e.g. “<td>”).

    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
     some
    -1.83
     Ausrüstung
    -1.70
    larım
    -1.66
     jaula
    -1.59
     schönsten
    -1.53
     possibly
    -1.53
    fondos
    -1.53
     culminated
    -1.52
     those
    -1.48
    '
    -1.45
    POSITIVE LOGITS
     meskipun
    1.68
     millón
    1.66
     tetapi
    1.64
     malen
    1.59
    while
    1.59
    
    1.57
     walaupun
    1.57
    at
    1.56
     twa
    1.56
    ner
    1.54
    Activations Density 0.000%

    No Known Activations