© 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. 65660
    Prev
    Next
    INDEX
    Explanations

    University Hospital

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

    proper nouns, particularly Thai names, institutions, and formal organizational titles.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on the formal names of Thai governmental or institutional organizations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    iowa
    -0.79
     jät
    -0.76
    complicated
    -0.75
    nerv
    -0.74
     feveral
    -0.74
    itse
    -0.72
    phyla
    -0.72
    हास
    -0.71
     neceffary
    -0.71
     ILLINOIS
    -0.70
    POSITIVE LOGITS
    velli
    0.92
     potentially
    0.88
     Shearer
    0.85
     queda
    0.78
    метров
    0.78
    onoi
    0.76
    ghts
    0.75
    ͆
    0.75
    λης
    0.75
     ホーム
    0.75
    Activations Density 0.008%

    No Known Activations