© 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. 123692
    Prev
    Next
    INDEX
    Explanations

    nitro- compounds and suffixes

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

    The neuron detects chemical compounds with the prefix "nitro" such as nitrobenzene, nitrofurantoin, and nitrotyrosine.

    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
    '
    -4.63
    {
    -2.98
     
    -2.83
    ?
    -2.63
     eas
    -2.52
     ‚
    -2.48
     crucial
    -2.42
     !!!!
    -2.39
    に対して
    -2.39
     myriad
    -2.38
    POSITIVE LOGITS
     While
    2.88
     That
    2.69
    一会儿
    2.53
     Despite
    2.42
     If
    2.42
    枼
    2.41
     镇
    2.36
    しました
    2.36
     Though
    2.33
     Unlike
    2.30
    Activations Density 0.003%

    No Known Activations