© 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. 34-GEMMASCOPE-RES-131K
    7. 76814
    Prev
    Next
    INDEX
    Explanations

    codes and urls

    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
     (
    -1.79
     in
    -1.62
     weirdly
    -1.55
    elsif
    -1.53
    toDouble
    -1.52
     nestled
    -1.51
     so
    -1.48
    
    -1.43
     strangely
    -1.43
     undeniably
    -1.42
    POSITIVE LOGITS
     verschillende
    1.89
     alcune
    1.80
    了很多
    1.77
    了不少
    1.77
    了一遍
    1.73
    了自己的
    1.69
     mentre
    1.68
     এবং
    1.67
    了自己
    1.66
    了一些
    1.63
    Activations Density 0.186%

    No Known Activations