© 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. 10-GEMMASCOPE-RES-131K
    7. 15246
    Prev
    Next
    INDEX
    Explanations

    product labels

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

    The neuron detects product spec headings or attribute labels (e.g. “Size:”, “Color:”, “Shipping & Returns”, “Brand”, “Material”) in a product description.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    訁
    -1.60
     verschillende
    -1.59
     today
    -1.46
    aabb
    -1.43
    氿
    -1.41
    衚
    -1.40
     equilíbrio
    -1.40
     Cualquier
    -1.37
    たしか
    -1.36
     térm
    -1.35
    POSITIVE LOGITS
     and
    1.74
    Some
    1.46
    ,
    1.43
    as
    1.42
    just
    1.34
     five
    1.34
    Just
    1.32
    9
    1.31
     fifteen
    1.31
     gives
    1.31
    Activations Density 0.043%

    No Known Activations