© 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. 106415
    Prev
    Next
    INDEX
    Explanations

    Canadian places and entities

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

    The neuron flags biographical descriptor words—especially nationality adjectives and occupation/sport terms.

    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
    消費者
    -0.79
    回覆
    -0.76
    Joanne
    -0.76
    ña
    -0.76
    ribusiness
    -0.75
    閻
    -0.72
    啊啊
    -0.72
     accedere
    -0.71
    ează
    -0.71
     Joanne
    -0.71
    POSITIVE LOGITS
     Dominion
    1.45
     lacrosse
    1.11
    Winnipeg
    1.02
     dominion
    1.01
    Domin
    1.01
     railway
    0.99
     Protestant
    0.96
     Toronto
    0.96
    Toronto
    0.96
     Canadian
    0.96
    Activations Density 0.054%

    No Known Activations