© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2083
    Prev
    Next
    INDEX
    Explanations

    tree traversals and orders

    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
    最强
    -0.77
    MyApp
    -0.77
    cerned
    -0.74
    IVer
    -0.72
    printStats
    -0.72
    çuk
    -0.71
    ichte
    -0.71
     richied
    -0.70
     Nacht
    -0.70
    EntryPoint
    -0.70
    POSITIVE LOGITS
     post
    1.64
     preorder
    1.61
     Post
    1.48
     pre
    1.38
     inorder
    1.34
    Post
    1.29
     Pre
    1.27
     postfix
    1.27
    中
    1.21
     PRE
    1.17
    Activations Density 0.020%

    No Known Activations