© 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. 103487
    Prev
    Next
    INDEX
    Explanations

    table tags like `<td>`

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

    ampersands in mathematical expressions or table formatting.

    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
    atação
    -2.11
     ordre
    -1.98
     kemer
    -1.98
     expérience
    -1.97
     adil
    -1.96
     saken
    -1.92
    rália
    -1.92
     illet
    -1.91
     estadounid
    -1.91
    푅
    -1.90
    POSITIVE LOGITS
     to
    2.39
     But
    2.31
            
    2.16
          
    1.84
    ar
    1.69
     utilizar
    1.61
     monotonous
    1.59
     pertenece
    1.58
    好的
    1.57
         
    1.56
    Activations Density 0.006%

    No Known Activations