© 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. 34-GEMMASCOPE-RES-131K
    7. 48805
    Prev
    Next
    INDEX
    Explanations

    names of organizations

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

    The neuron flags mentions of formal organizations, institutions, and their acronyms.

    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
     autres
    -1.18
     dupla
    -1.14
     injus
    -1.07
     aventura
    -1.07
     oreja
    -1.06
     colina
    -1.06
     spolup
    -1.06
    𓐍
    -1.06
     consulte
    -1.05
     autre
    -1.02
    POSITIVE LOGITS
     National
    2.17
     Department
    1.93
    National
    1.77
     Center
    1.70
     Institute
    1.64
     University
    1.59
     American
    1.59
     Ministry
    1.59
     Office
    1.58
     United
    1.57
    Activations Density 0.223%

    No Known Activations