© 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. 34-GEMMASCOPE-RES-131K
    4. 81367
    Prev
    Next
    INDEX
    Explanations

    selectivity, stereochemistry, enantioselectivity

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

    chemical or biochemical terms related to stereoselectivity and enantiomers.

    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_34/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
     ITC
    -0.77
    销毁
    -0.70
    रि
    -0.69
     வரு
    -0.68
     Sabine
    -0.67
     Gian
    -0.66
     매
    -0.65
    姻
    -0.64
     Bloomington
    -0.64
    uten
    -0.64
    POSITIVE LOGITS
     selective
    6.63
     Selective
    6.06
    Selective
    5.94
    selective
    5.94
     selectivity
    5.78
     selectively
    5.28
     sele
    4.47
     Sele
    4.44
    sele
    4.38
    Sele
    4.09
    Activations Density 0.294%

    No Known Activations