© 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. 38841
    Prev
    Next
    INDEX
    Explanations

    amino acids, fatty acids, nucleic acids

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

    This neuron detects scientific and chemical terminology, particularly the term "acids" in various contexts like "amino acids," "fatty acids," and "nucleic acids."

    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
    
    -2.30
    tedì
    -2.20
    ,’’
    -2.14
    The
    -2.11
    ll
    -2.05
    柵
    -2.03
    żli
    -2.02
    やお
    -2.02
     owing
    -2.00
     Wohnen
    -2.00
    POSITIVE LOGITS
     \&
    2.69
    Ꮗ
    2.48
    遢
    2.20
    一番
    2.03
    AN
    2.02
     hét
    2.02
     acids
    2.00
     amplificador
    1.98
     jopa
    1.92
     ketika
    1.90
    Activations Density 0.006%

    No Known Activations