© 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. 128246
    Prev
    Next
    INDEX
    Explanations

    serine protease/phosphorylation/kinase

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

    The neuron detects mentions of the amino acid serine in scientific contexts.

    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
     Then
    -3.19
     แล้ว
    -2.36
     EVERYTHING
    -2.23
    
    -2.23
    ERS
    -2.19
    鸝
    -2.13
     damn
    -2.08
    呿
    -2.03
     ambiguous
    -2.02
     BUT
    -2.00
    POSITIVE LOGITS
    昃
    2.11
    What
    1.87
     compreender
    1.86
     είναι
    1.84
    </h2>
    1.83
    昞
    1.81
    欝
    1.77
    чини
    1.74
    餮
    1.70
    nvarchar
    1.69
    Activations Density 0.068%

    No Known Activations