© 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. 10-GEMMASCOPE-RES-131K
    4. 102865
    Prev
    Next
    INDEX
    Explanations

    aspartic, asparagine, concanavalin A

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

    This neuron activates on amino acid names and biochemical terms, particularly "asparagine," "alanine," and other chemical compounds.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron selectively activates on occurrences of the amino acid name “asparagine.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ⚣
    -3.28
    𓋼
    -2.66
    蟶
    -2.55
    渽
    -2.34
    鹩
    -2.34
    );
    -2.33
     позволит
    -2.30
    臯
    -2.25
    蜑
    -2.16
    🧌
    -2.14
    POSITIVE LOGITS
    &
    2.84
     &
    2.67
    皷
    2.59
    t
    2.52
     &#
    2.36
     HAVE
    2.34
    勦
    2.33
    .&
    2.31
    ↵↵
    2.27
    飧
    2.25
    Activations Density 0.001%

    No Known Activations