© 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. 48264
    Prev
    Next
    INDEX
    Explanations

    spoiled, rotten, or expired

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

    signs of food spoilage, preservation issues, and shelf-life concerns.

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

    The neuron detects mentions of a product’s or material’s ability to resist change or environmental influences (i.e. stability or durability).

    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
     sander
    -0.80
     cleaner
    -0.77
    pee
    -0.75
     defoli
    -0.74
     Cleaner
    -0.74
     eucalyptus
    -0.72
    **:
    -0.72
    leon
    -0.71
    iga
    -0.70
    boot
    -0.70
    POSITIVE LOGITS
     spoiled
    2.98
     spoil
    2.41
     spoiling
    2.27
     rotten
    2.25
     spoilt
    2.22
     expired
    1.99
     mold
    1.88
    spo
    1.88
     spoils
    1.87
     spo
    1.79
    Activations Density 0.026%

    No Known Activations