© 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. 42309
    Prev
    Next
    INDEX
    Explanations

    companies, names, or identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     sitios
    -1.69
     hoge
    -1.63
     welkom
    -1.59
     mesaj
    -1.58
    鷙
    -1.56
     supprimer
    -1.55
     sukker
    -1.55
     cómoda
    -1.55
    🩱
    -1.55
     帅气
    -1.54
    POSITIVE LOGITS
     for
    2.16
    They
    1.59
     in
    1.59
        
    1.59
    Then
    1.57
     "
    1.56
     by
    1.52
    .
    1.51
          
    1.50
         
    1.49
    Activations Density 0.010%

    No Known Activations