© 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. 53839
    Prev
    Next
    INDEX
    Explanations

    lacto-containing biological substances

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

    terms related to bacteria and dairy proteins, particularly "Lacto" prefixed words like Lactobacillus and lactoferrin.

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

    The neuron fires on the substring “lacto,” i.e. biological terms beginning with the prefix “lacto.”

    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
    uality
    -0.76
     Caf
    -0.73
    écial
    -0.70
    Reserved
    -0.70
    Fou
    -0.69
     XCTest
    -0.69
    counters
    -0.68
    timeScale
    -0.68
    Andre
    -0.66
    tauan
    -0.66
    POSITIVE LOGITS
     dehydrogenase
    0.85
     πριν
    0.79
     حسین
    0.77
    teal
    0.72
    energ
    0.70
    quivado
    0.70
     select
    0.69
    數量
    0.67
    ッズ
    0.67
    業者
    0.65
    Activations Density 0.077%

    No Known Activations