© 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. 30260
    Prev
    Next
    INDEX
    Explanations

    united nations and related entities

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

    This neuron selectively picks out tokens that form formal publication header elements—e.g. report-title words (“Development,” “Report,” “Programme,” “Index,” “United Nations”) and the year digits.

    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
    ᵍ
    -0.85
    рых
    -0.75
     Identifier
    -0.74
    Trọng
    -0.74
     fillings
    -0.74
    occuper
    -0.74
     tepi
    -0.73
    лько
    -0.71
     esporte
    -0.71
     печени
    -0.70
    POSITIVE LOGITS
     UNDP
    1.74
    UNDP
    1.67
     holt
    0.84
     Crisis
    0.82
     boto
    0.81
     crisis
    0.77
    GEF
    0.73
     اند
    0.72
     Arora
    0.72
     plastique
    0.72
    Activations Density 0.009%

    No Known Activations