© 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. 24927
    Prev
    Next
    INDEX
    Explanations

    organizations and media outlets

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

    This neuron primarily detects named entities—especially organization and institution 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
     on
    -1.20
     experience
    -1.17
     after
    -1.16
     microfibra
    -1.13
     Lainnya
    -1.13
     one
    -1.09
    tadır
    -1.08
     fronte
    -1.07
     spend
    -1.06
    رق
    -1.06
    POSITIVE LOGITS
     puissante
    1.43
    第一时间
    1.27
     worldwide
    1.27
     ибо
    1.22
    ACCIÓN
    1.21
    ouac
    1.20
     sạc
    1.19
    小伙伴
    1.18
    んでしょう
    1.15
    ၜ
    1.15
    Activations Density 0.069%

    No Known Activations