© 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. 77216
    Prev
    Next
    INDEX
    Explanations

    code definitions

    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
     also
    -1.08
     its
    -0.90
    closeConnection
    -0.88
     if
    -0.87
    rmtree
    -0.84
     ControllerBase
    -0.83
     either
    -0.81
     już
    -0.79
    updateUI
    -0.79
     especially
    -0.78
    POSITIVE LOGITS
    創造
    1.16
    glGen
    1.06
    创建一个
    1.04
     생성
    1.03
     created
    1.02
    创建
    1.02
     first
    1.00
    δη
    1.00
     creating
    0.98
     创建
    0.98
    Activations Density 0.037%

    No Known Activations