© 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. 102161
    Prev
    Next
    INDEX
    Explanations

    end-to-end or point-to-point connections

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

    the phrase "end-to-end" in technical contexts.

    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
    .
    -2.58
     about
    -1.84
     Much
    -1.77
     allgemeinen
    -1.73
    Of
    -1.70
    {
    -1.64
    ೣ
    -1.63
     
    -1.62
     Allgemeinen
    -1.61
    y
    -1.57
    POSITIVE LOGITS
    ଃ
    2.16
     sende
    1.78
    礽
    1.72
    σμο
    1.71
    ÁCT
    1.69
    嶠
    1.68
    
    1.67
     llenos
    1.66
    💯
    1.65
     entree
    1.63
    Activations Density 0.005%

    No Known Activations