© 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. 130598
    Prev
    Next
    INDEX
    Explanations

    aryl and phenyl groups

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

    This neuron detects chemical compound names, particularly aromatic compounds and benzene derivatives in scientific contexts.

    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
     they
    -2.02
     måtte
    -1.56
     necessaria
    -1.52
    也没
    -1.44
    менить
    -1.42
    当然
    -1.41
    ιος
    -1.37
    咣
    -1.36
     Aplikasi
    -1.35
    ◳
    -1.35
    POSITIVE LOGITS
    since
    1.63
     realizando
    1.52
     eventdata
    1.48
     profundas
    1.47
    upuncture
    1.47
     EconPapers
    1.46
     provocado
    1.42
    '
    1.41
    lgari
    1.40
    Toeschouwers
    1.37
    Activations Density 0.122%

    No Known Activations