© 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. 34-GEMMASCOPE-RES-131K
    7. 48359
    Prev
    Next
    INDEX
    Explanations

    programming keywords and libraries

    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_34/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
     Remain
    -0.88
    remain
    -0.87
    zhen
    -0.86
    胛
    -0.84
    nez
    -0.82
    нки
    -0.81
     each
    -0.81
    atin
    -0.79
    ($("#
    -0.79
     بی
    -0.78
    POSITIVE LOGITS
     ALT
    0.86
    dze
    0.85
    pula
    0.82
    利
    0.81
     排行
    0.79
     meil
    0.78
     ANN
    0.77
    Skład
    0.74
    Whilst
    0.74
    惘
    0.74
    Activations Density 0.007%

    No Known Activations