© 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. 8460
    Prev
    Next
    INDEX
    Explanations

    organization statements

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

    The neuron detects parenthetical appearances of formal organization names and their acronyms (e.g. “World Health Organization (WHO)”).

    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
    ",
    -1.55
    ."
    -1.55
    如同
    -1.48
     Mereka
    -1.48
    Şi
    -1.48
    endalikan
    -1.45
    ',
    -1.45
    ༛
    -1.45
     endforeach
    -1.44
     EconPapers
    -1.44
    POSITIVE LOGITS
    ↵↵
    1.76
    揼
    1.48
    ଶ
    1.44
     cruda
    1.41
     vasca
    1.41
     Torneo
    1.38
    㩒
    1.37
     $_(
    1.37
    却被
    1.36
     years
    1.35
    Activations Density 0.153%

    No Known Activations