© 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. 1102
    Prev
    Next
    INDEX
    Explanations

    LED and LCD technology

    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
    流石
    -0.92
    ホント
    -0.91
    恥ず
    -0.90
     OLED
    -0.89
    凄く
    -0.89
    あぁ
    -0.89
    ときに
    -0.87
     sesama
    -0.87
     LED
    -0.86
    色んな
    -0.85
    POSITIVE LOGITS
     technology
    1.47
    technology
    1.20
     tecnología
    1.09
     افراد
    0.98
    fører
    0.94
     TECHNOLOGY
    0.93
    TECHNOLOGY
    0.92
     فناوری
    0.91
     technolog
    0.91
    Наталья
    0.91
    Activations Density 0.087%

    No Known Activations