© 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. 34-GEMMASCOPE-RES-131K
    7. 62711
    Prev
    Next
    INDEX
    Explanations

    table parts

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

    The neuron fires on product‐specification terms—especially furniture or hardware component words (e.g. panels, tables, legs, power components).

    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
     shingles
    -0.76
     ceilings
    -0.75
     drywall
    -0.72
    illoma
    -0.71
     stoned
    -0.70
     reggae
    -0.70
    INGRED
    -0.70
     okna
    -0.69
    おり
    -0.68
    arod
    -0.67
    POSITIVE LOGITS
     table
    1.22
     столе
    1.21
     Table
    1.20
     legs
    1.11
    桌
    1.07
     tabletop
    1.05
     tops
    0.99
     TABLE
    0.96
     leg
    0.94
     Tisch
    0.94
    Activations Density 0.031%

    No Known Activations