© 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. 57376
    Prev
    Next
    INDEX
    Explanations

    latex package imports

    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
     Uncategorized
    -0.90
     retirar
    -0.89
    って何
    -0.88
    servant
    -0.88
    lacoste
    -0.87
    strongly
    -0.84
     fortalecer
    -0.82
     dinámico
    -0.81
    unisex
    -0.81
     others
    -0.81
    POSITIVE LOGITS
     {
    0.82
     [
    0.81
    Μ
    0.81
    Α
    0.79
    Gecko
    0.76
    bor
    0.73
     CST
    0.73
    !».
    0.72
    ก
    0.71
     Jorge
    0.71
    Activations Density 0.001%

    No Known Activations