© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48535
    Prev
    Next
    INDEX
    Explanations

    product attributes and PIM

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

    This neuron responds strongly to structured-data field names and related identifiers (e.g. “categories,” “product_id,” “videos.formats,” etc.) in code or query 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
    כות
    -0.76
     продаже
    -0.75
     dịch
    -0.75
     sudden
    -0.73
     urbanos
    -0.73
     calendario
    -0.71
     lighten
    -0.71
     Orten
    -0.70
    heated
    -0.69
    LATE
    -0.69
    POSITIVE LOGITS
     manufacturer
    1.09
     PIM
    1.06
     EAN
    1.06
    pim
    1.04
     attribute
    1.02
     UPC
    0.97
     attributes
    0.91
     Manufacturer
    0.90
    UPC
    0.87
    MPN
    0.87
    Activations Density 0.041%

    No Known Activations