© 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. 112022
    Prev
    Next
    INDEX
    Explanations

    require statements

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

    assignment operators in code, particularly the equals sign used for variable assignment.

    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
    Moreover
    -1.80
    Furthermore
    -1.70
    푆
    -1.66
    秶
    -1.63
    訁
    -1.59
     viens
    -1.53
    焌
    -1.50
    菹
    -1.48
     indepen
    -1.48
    ܇
    -1.46
    POSITIVE LOGITS
     or
    1.86
    \
    1.68
    ﹶ
    1.61
     يوسف
    1.59
    {
    1.55
    }{*}{}
    1.51
     _{
    1.42
     certificados
    1.38
     destinée
    1.34
     Departamento
    1.34
    Activations Density 0.048%

    No Known Activations