© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81552
    Prev
    Next
    INDEX
    Explanations

    leucine zipper

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

    words or phrases related to file extensions or technical computer terminology.

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

    The neuron strongly activates on occurrences of the amino‐acid name “leucine.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    patrol
    -0.68
     Wör
    -0.66
    libra
    -0.65
    tiled
    -0.65
     上海
    -0.65
    〢
    -0.64
     Weiterbildung
    -0.64
    liminary
    -0.62
     septembrie
    -0.62
    atguigu
    -0.60
    POSITIVE LOGITS
     zipper
    3.83
     zip
    3.80
     ZIP
    3.38
    zip
    3.13
     Zip
    3.11
     zippers
    3.06
    ZIP
    2.72
    Zip
    2.70
     Zipper
    2.67
     zi
    2.47
    Activations Density 0.056%

    No Known Activations