© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83876
    Prev
    Next
    INDEX
    Explanations

    folklore, luggage, glassware, swimwear

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

    The neuron fires on uncountable mass‐noun category words—things like footwear, folklore, cookware, glassware, luggage, etc.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ing
    -2.53
    iarkan
    -2.28
     melanjutkan
    -2.27
    缑
    -2.27
     Despite
    -2.27
    ‘
    -2.27
     memastikan
    -2.25
    medriver
    -2.23
     getNome
    -2.22
     olev
    -2.19
    POSITIVE LOGITS
     astonishing
    2.59
     quintessential
    2.58
    idjan
    2.56
     flamboyant
    2.45
     nuevos
    2.45
    they
    2.44
     Geschenk
    2.44
     แต่
    2.39
     disgruntled
    2.33
    蹰
    2.33
    Activations Density 0.001%

    No Known Activations