© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98174
    Prev
    Next
    INDEX
    Explanations

    white organic light-emitting diodes

    np_acts-logits-general · gemini-2.5-flash-lite

    terminology related to light-emitting diodes (LEDs) or organic light-emitting diodes (OLEDs).

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    atico
    -0.74
    NS
    -0.71
     кү
    -0.69
    ʒ
    -0.69
    २
    -0.69
     communities
    -0.69
     dużo
    -0.69
    honneur
    -0.68
    _{\
    -0.67
    uy
    -0.67
    POSITIVE LOGITS
     luminance
    1.10
     OLED
    1.06
    OLED
    0.86
     phosp
    0.85
    phosph
    0.80
     device
    0.80
     devices
    0.79
    折磨
    0.79
     yogur
    0.78
    wouldn
    0.77
    Activations Density 0.085%

    No Known Activations