© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41553
    Prev
    Next
    INDEX
    Explanations

    MCU, microbiota, Karim Benzema, Gibbs free energy

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

    This neuron detects references to microbiota and microorganisms as well as acronyms like MCU.

    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
    烔
    -2.72
    .‏
    -2.72
    勠
    -2.44
    也
    -2.42
    纮
    -2.41
    璨
    -2.41
    哢
    -2.30
    躥
    -2.30
    os
    -2.25
    ־
    -2.23
    POSITIVE LOGITS
    ︲
    2.94
    ⚌
    2.89
    鹛
    2.86
    OUTUBE
    2.72
    〣
    2.69
    妧
    2.58
    ᛬
    2.56
    ⇿
    2.53
    𓋼
    2.52
    B
    2.47
    Activations Density 0.006%

    No Known Activations