© 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. 62651
    Prev
    Next
    INDEX
    Explanations

    honours and designations

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

    The neuron detects honorific post–nominal initials (e.g. CM, OBE, SBS) that denote awards or orders.

    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
     Defeat
    -0.76
     McCarty
    -0.69
    atre
    -0.68
    collect
    -0.67
    DDDD
    -0.66
     Jow
    -0.65
    ablecer
    -0.65
     PLW
    -0.64
    onus
    -0.63
    Gfx
    -0.63
    POSITIVE LOGITS
     MBE
    2.08
     OBE
    1.70
     BEM
    1.11
     Order
    1.05
     Member
    1.02
     Officer
    0.97
    Order
    0.96
     CBE
    0.96
    Officer
    0.90
    Member
    0.88
    Activations Density 0.056%

    No Known Activations