© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 730
    Prev
    Next
    INDEX
    Explanations

    biological derivatives

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

    The neuron identifies the word "derived" in biological/scientific contexts, especially when describing the source of cells, tissues, or substances.

    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
    🎼
    -1.65
     departament
    -1.61
     symbole
    -1.59
     cloche
    -1.52
     zodia
    -1.52
     fatale
    -1.52
     domestique
    -1.52
     veau
    -1.51
     sirop
    -1.49
    
    -1.48
    POSITIVE LOGITS
     and
    2.16
    :
    1.48
     χωρίς
    1.30
    (
    1.27
     either
    1.24
    -
    1.22
    涙
    1.21
     such
    1.20
     proporcionar
    1.19
     自動
    1.18
    Activations Density 0.144%

    No Known Activations