© 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. 22-GEMMASCOPE-RES-131K
    7. 16506
    Prev
    Next
    INDEX
    Explanations

    family relationships, siblings

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

    The neuron detects kinship terms (e.g. father, brother, son) in biographical text.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     only
    -1.38
     with
    -1.14
     new
    -1.09
     simple
    -1.08
     that
    -1.08
     never
    -1.00
     vorhandenen
    -0.94
     gewünschten
    -0.94
     verfügb
    -0.93
     this
    -0.92
    POSITIVE LOGITS
    eſt
    1.11
    %#
    1.00
     sukses
    0.97
     perpétu
    0.96
     gema
    0.95
    ├──
    0.94
     célèbres
    0.93
     litro
    0.91
     akti
    0.90
    カビ
    0.90
    Activations Density 0.050%

    No Known Activations