© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93432
    Prev
    Next
    INDEX
    Explanations

    tryptophan

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

    the amino acid tryptophan and related biochemical compounds.

    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
    weeney
    -0.75
     ทำ
    -0.74
     inhum
    -0.72
    どく
    -0.72
     красивая
    -0.69
    uxi
    -0.69
     Calib
    -0.68
     revoir
    -0.67
    pril
    -0.66
    indere
    -0.66
    POSITIVE LOGITS
     trypto
    1.88
     Trp
    1.27
     Try
    1.11
    TRY
    0.99
     try
    0.93
     indo
    0.93
     serotonin
    0.91
    Try
    0.88
     tryp
    0.87
    taca
    0.80
    Activations Density 0.135%

    No Known Activations