© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19283
    Prev
    Next
    INDEX
    Explanations

    scientific names and brands

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

    scientific or taxonomic names in various fields including biology, medicine, and law.

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

    The neuron fires strongly on Latin scientific names of organisms (genus and species).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ↵↵
    -2.73
    扨
    -2.64
    蟜
    -2.44
     Gedicht
    -2.22
     they
    -2.22
    乄
    -2.20
     Aceite
    -2.13
     akces
    -2.13
     festen
    -2.09
     Aufwand
    -2.09
    POSITIVE LOGITS
     for
    2.88
     of
    2.81
    
    2.36
     or
    2.14
     to
    2.14
    ↵
    2.13
    泱
    2.05
    出了一
    1.99
     utilizzati
    1.94
    、《
    1.90
    Activations Density 0.288%

    No Known Activations