© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65665
    Prev
    Next
    INDEX
    Explanations

    National Oceanographic Institute

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

    words and phrases related to Southeast Asian countries, cultures, and history.

    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
    naby
    -0.79
    想要的
    -0.78
     MSE
    -0.75
    amir
    -0.75
    phors
    -0.72
    THR
    -0.71
    같이
    -0.71
     ulicy
    -0.70
     работают
    -0.70
    ignet
    -0.70
    POSITIVE LOGITS
     temple
    0.94
     Cambodia
    0.76
     temples
    0.75
     Vishnu
    0.75
    Brak
    0.71
     Ahmad
    0.70
    邃
    0.70
     ensemble
    0.70
     csal
    0.69
     غرفة
    0.69
    Activations Density 0.011%

    No Known Activations