© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39731
    Prev
    Next
    INDEX
    Explanations

    American professional associations

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

    The main thing this neuron does is detect mentions of formal organization names—especially American professional associations, boards, and societies.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Estos
    -1.41
     who
    -1.38
     Эти
    -1.35
     iliş
    -1.30
     razões
    -1.30
    肆
    -1.25
     CONCERN
    -1.24
    También
    -1.21
    ſſen
    -1.21
     avec
    -1.21
    POSITIVE LOGITS
     eléctricas
    1.35
     utafiti
    1.27
     anything
    1.26
     bagay
    1.25
     blah
    1.19
     magis
    1.18
     litio
    1.17
     manca
    1.16
     ヶ
    1.16
    bảng
    1.15
    Activations Density 0.063%

    No Known Activations