© 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. 16617
    Prev
    Next
    INDEX
    Explanations

    business celebrates

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

    The neuron fires strongly on named organizations, agencies, institutions, and similar entity names.

    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
    viamo
    -1.09
    Additional
    -1.01
    Add
    -1.00
    ׇ
    -0.99
     razões
    -0.94
    Adding
    -0.94
     them
    -0.93
    itori
    -0.91
     иллюстрация
    -0.91
    add
    -0.88
    POSITIVE LOGITS
     his
    1.02
     currently
    0.99
     کنم
    0.95
     important
    0.95
    在他的
    0.94
    ּוֹ
    0.94
     CRUZ
    0.90
     criticized
    0.90
    ों
    0.88
    ־ה
    0.88
    Activations Density 0.063%

    No Known Activations