© 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. 10-GEMMASCOPE-RES-131K
    7. 124629
    Prev
    Next
    INDEX
    Explanations

    mosquito bites and diseases

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

    mosquitoes and their related terms like "mosquito-borne" and specific species names.

    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_10/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
    T
    -2.64
    quelize
    -2.53
    .”
    -2.47
    o
    -2.47
     –
    -2.34
     новой
    -2.31
    一定是
    -2.27
    ar
    -2.22
    u
    -2.19
    又在
    -2.17
    POSITIVE LOGITS
     What
    2.19
    
    2.17
    鈇
    2.17
     iſt
    2.14
    驀
    2.11
    鱘
    2.09
    
    2.08
     сказать
    2.06
    襤
    2.06
     wodurch
    2.05
    Activations Density 0.004%

    No Known Activations