© 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. 22-GEMMASCOPE-RES-131K
    7. 66460
    Prev
    Next
    INDEX
    Explanations

    chemical element symbols

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

    chemical elements and symbols in scientific papers.

    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_22/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
     eds
    -2.09
     diretor
    -1.88
    ſelves
    -1.84
     assolu
    -1.76
     llevará
    -1.75
    蜡
    -1.73
     clínico
    -1.73
     científico
    -1.70
     prazo
    -1.69
     retrô
    -1.69
    POSITIVE LOGITS
     &
    1.91
    念头
    1.87
    そうですが
    1.76
    其妙
    1.76
    鴴
    1.71
    麻煩
    1.60
    进了
    1.56
     was
    1.55
    兩種
    1.55
    彼の
    1.52
    Activations Density 0.060%

    No Known Activations