© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77608
    Prev
    Next
    INDEX
    Explanations

    establishment of organizations or entities

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

    The neuron specializes in spotting mentions of formal organization or policy names and other multiword proper‐noun titles.

    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
     sắp
    -0.99
     Zusammensetzung
    -0.86
     maneiras
    -0.84
    काश
    -0.84
    Примеча
    -0.83
    الط
    -0.82
     aktuellen
    -0.81
     변경
    -0.80
     fraî
    -0.80
    UGHS
    -0.79
    POSITIVE LOGITS
     national
    1.37
     new
    1.22
     mechanism
    1.20
     entity
    1.13
     National
    1.08
     institute
    1.03
     dedicated
    1.02
     "
    1.00
     separate
    1.00
     permanent
    0.98
    Activations Density 0.072%

    No Known Activations