© 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. 61014
    Prev
    Next
    INDEX
    Explanations

    catalysis and chemical variables

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

    chemistry and mathematics terminology, particularly focusing on chemical compounds, equations, and analytical methods.

    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
     there
    -1.48
     giapponese
    -1.42
    ቷ
    -1.34
     udało
    -1.33
     is
    -1.32
     베
    -1.31
    いぐるみ
    -1.30
     składa
    -1.25
     کسی
    -1.23
    。<
    -1.23
    POSITIVE LOGITS
     for
    2.30
     сумка
    1.52
    viembre
    1.50
     упаковка
    1.43
    ">(</
    1.42
     offrir
    1.39
     étrang
    1.38
     connexe
    1.38
     الحد
    1.31
    shadowRadius
    1.30
    Activations Density 0.029%

    No Known Activations