© 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. 62563
    Prev
    Next
    INDEX
    Explanations

    places and their keepers

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

    The neuron fires strongly on nouns denoting types of buildings or enclosed spaces (e.g. stable, garage, cellar door, showroom, greenhouse, warehouse).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Courthouse
    -0.80
    heartedly
    -0.79
    stache
    -0.77
     trumpets
    -0.77
    laa
    -0.77
     ujedno
    -0.76
     HOPE
    -0.76
     Offices
    -0.76
    ングル
    -0.75
     cirka
    -0.75
    POSITIVE LOGITS
     owner
    1.13
     keeper
    1.10
     Keeper
    1.05
     dwellers
    1.04
     worker
    1.03
     Keepers
    1.01
     contents
    1.00
     workers
    0.98
     manager
    0.98
     doors
    0.98
    Activations Density 0.056%

    No Known Activations