© 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. 22-GEMMASCOPE-RES-131K
    7. 54116
    Prev
    Next
    INDEX
    Explanations

    synthesis and subsequent actions

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

    The neuron identifies the word "synthesis" or related terms like "synthetic" in scientific contexts, often paired with chemical or biological research terminology.

    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_22/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
     was
    -2.91
     are
    -2.84
    ’-
    -2.56
    am
    -2.56
    ’;
    -2.41
    鹛
    -2.38
     "
    -2.36
     differs
    -2.30
    啻
    -2.30
    !’
    -2.27
    POSITIVE LOGITS
     Répondre
    2.69
    ༛
    2.64
    鎹
    2.58
    In
    2.45
     Soyez
    2.41
    杙
    2.39
    躝
    2.38
     табле
    2.34
    鋱
    2.33
    следования
    2.27
    Activations Density 0.024%

    No Known Activations