© 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. 21849
    Prev
    Next
    INDEX
    Explanations

    aggressive nature, behaviors, treatments

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

    The neuron is looking for the adjective "aggressive" and related terms describing intensity or severity.

    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
     \"
    -3.17
     {
    -3.00
    {
    -2.98
     we
    -2.91
     ``
    -2.81
                
    -2.72
    ↵↵
    -2.70
    (
    -2.67
    -2.55
     a
    -2.53
    POSITIVE LOGITS
    愎
    2.95
    Важно
    2.77
    𓄹
    2.72
    鋮
    2.53
     啦
    2.52
    しており
    2.50
    地说
    2.48
    ጮ
    2.42
    欉
    2.42
    笈
    2.41
    Activations Density 0.003%

    No Known Activations