© 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. 34-GEMMASCOPE-RES-131K
    7. 59099
    Prev
    Next
    INDEX
    Explanations

    food processing and safety testing

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

    scientific language related to food science, particularly food processing and preservation techniques.

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

    The neuron detects technical scientific language, particularly measurements, numbers, and domain-specific terminology in research contexts.

    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
     ripe
    -0.79
     EAS
    -0.75
    pirable
    -0.71
    重大
    -0.69
     възможно
    -0.68
    textField
    -0.67
    ينما
    -0.67
    glPopMatrix
    -0.66
     Май
    -0.66
    优惠
    -0.66
    POSITIVE LOGITS
     Fail
    0.83
     épices
    0.79
     Swat
    0.76
     USDA
    0.76
     kateg
    0.75
    ecore
    0.75
    क्षा
    0.75
     Erfolge
    0.75
     Failed
    0.73
    שא
    0.72
    Activations Density 0.032%

    No Known Activations