© 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. 62450
    Prev
    Next
    INDEX
    Explanations

    board games

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

    The neuron fires on capitalized proper nouns and titles—that is, named entities like game names, people’s names, and organizations.

    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
    ashion
    -0.92
    暧
    -0.90
     Globe
    -0.84
     antiviral
    -0.84
    ندق
    -0.82
    addGap
    -0.82
    {~
    -0.80
     Country
    -0.80
     representative
    -0.80
     Member
    -0.79
    POSITIVE LOGITS
     tabletop
    1.80
     gaming
    1.66
     miniatures
    1.48
    RPG
    1.44
    gaming
    1.41
     games
    1.31
     game
    1.30
     gamers
    1.29
     hobby
    1.27
    Gaming
    1.26
    Activations Density 0.083%

    No Known Activations