© 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. 3727
    Prev
    Next
    INDEX
    Explanations

    acetyl-CoA and related compounds

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

    biochemical compounds and enzymes related to CoA (coenzyme A) and carnitine in scientific literature.

    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
    👊
    -1.78
    باء
    -1.73
    by
    -1.65
     RESERVE
    -1.59
     BitSet
    -1.59
     twa
    -1.55
    C
    -1.52
     CATEGORY
    -1.52
     DENSITY
    -1.52
     wewnętr
    -1.50
    POSITIVE LOGITS
     Regarding
    1.93
    卺
    1.80
     Someone
    1.74
     Careful
    1.73
     одну
    1.68
    場に
    1.66
     Können
    1.66
     bekämp
    1.63
     don
    1.61
     feiern
    1.61
    Activations Density 0.023%

    No Known Activations