© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111423
    Prev
    Next
    INDEX
    Explanations

    configuration prefixes

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

    the word "prefix" followed by an assignment operator or colon in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ↵↵
    -2.03
      
    -1.96
    .
    -1.93
    {
    -1.86
     and
    -1.72
     it
    -1.72
     मेरे
    -1.70
     But
    -1.67
     noiva
    -1.59
        
    -1.57
    POSITIVE LOGITS
     jopa
    1.94
     laajenta
    1.92
     parfü
    1.88
     julk
    1.83
     beiden
    1.77
    Tapi
    1.73
     berge
    1.66
     tehdä
    1.66
    ‪.‬‬
    1.66
     tavo
    1.65
    Activations Density 0.006%

    No Known Activations