© 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. 41807
    Prev
    Next
    INDEX
    Explanations

    Lactobacillus, lacto, Commando, Rancho, Candida

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

    This neuron detects the term "Lacto" in scientific contexts, particularly related to bacteria (Lactobacillus) and biological compounds.

    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
    鬭
    -2.63
    蚡
    -2.59
    tigte
    -2.47
    亖
    -2.45
    甞
    -2.44
    可爱
    -2.44
    乆
    -2.39
    
    -2.39
     parachoque
    -2.36
     capuz
    -2.36
    POSITIVE LOGITS
    ↵↵
    3.56
    ");
    2.89
    A
    2.81
    "
    2.78
    in
    2.66
     quando
    2.64
     necesario
    2.47
    }{
    2.45
    ());
    2.31
    ａ
    2.31
    Activations Density 0.010%

    No Known Activations