© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21069
    Prev
    Next
    INDEX
    Explanations

    synthesis of molecules

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

    biological or biochemical processes related to synthesis, especially in the context of metabolism, proteins, and cellular functions.

    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
    or
    -1.68
    even
    -1.66
     kwanza
    -1.61
     munt
    -1.51
     elemente
    -1.50
    甚至是
    -1.47
     pecu
    -1.43
    ou
    -1.40
    s
    -1.39
    if
    -1.38
    POSITIVE LOGITS
     about
    1.82
     fomentar
    1.63
     Unterneh
    1.47
    acaktır
    1.39
     Verständ
    1.38
     Erinner
    1.37
     production
    1.36
     Gedächt
    1.32
     valuable
    1.32
     Since
    1.32
    Activations Density 0.179%

    No Known Activations