© 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. 106247
    Prev
    Next
    INDEX
    Explanations

    names starting with Dar

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

    This neuron detects tokens beginning with the letters “Dar,” primarily personal names like Darling, Darron, and Darrion.

    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
     bará
    -0.93
     imparti
    -0.83
    UCA
    -0.81
    愫
    -0.80
    nees
    -0.79
     wonderland
    -0.78
    cir
    -0.75
     reco
    -0.72
     qualifiers
    -0.71
    estars
    -0.71
    POSITIVE LOGITS
     Buds
    0.80
     sew
    0.78
    Antes
    0.77
    switches
    0.74
     shoved
    0.73
     オープン
    0.73
    gross
    0.71
     imprisonment
    0.70
     betrifft
    0.70
     مورد
    0.69
    Activations Density 0.022%

    No Known Activations