© 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. 127891
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on mentions of close personal relations—especially “family” (and related words for loved ones).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    family activities

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     or
    -1.33
     for
    -1.08
     might
    -1.04
     will
    -1.04
     can
    -0.98
    itamente
    -0.96
     from
    -0.95
    Ọ
    -0.94
     For
    -0.93
     about
    -0.93
    POSITIVE LOGITS
    stretched
    1.16
    ҩ
    1.10
     siè
    1.09
    蘩
    1.09
    newnode
    1.09
    berra
    1.09
    änglich
    1.08
    ggars
    1.06
     Meille
    1.04
    🫅
    1.04
    Activations Density 0.003%

    No Known Activations