© 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. 19595
    Prev
    Next
    INDEX
    Explanations

    metabolites

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

    The neuron identifies biochemical or scientific terms related to "metabolites" in scientific texts.

    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
    "
    -3.27
    すでに
    -3.02
    or
    -2.77
    すぐに
    -2.64
    いつでも
    -2.55
    e
    -2.42
     dasarnya
    -2.28
    ほとんど
    -2.28
    a
    -2.27
    あっという間に
    -2.25
    POSITIVE LOGITS
     прошел
    2.73
    谖
    2.64
    絝
    2.63
    搥
    2.59
    kurtka
    2.48
    贗
    2.48
    __))
    2.45
    婳
    2.38
     Could
    2.36
     für
    2.34
    Activations Density 0.018%

    No Known Activations