© 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. 100354
    Prev
    Next
    INDEX
    Explanations

    international organizations and agencies

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

    The neuron fires on mentions of formal international organizations or agencies (e.g. names containing “International,” “Organization,” “UN,” etc.).

    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
     then
    -1.32
    mployment
    -1.17
    Lots
    -1.14
     necess
    -1.14
     Estamos
    -1.09
    Enciclopedia
    -1.07
    čných
    -1.07
    erequisite
    -1.05
    および
    -1.03
    ffre
    -1.02
    POSITIVE LOGITS
    愍
    1.16
    cibly
    1.16
    >>>>
    1.13
     sabias
    1.13
     chers
    1.13
     their
    1.12
    cartItems
    1.11
    strator
    1.11
    zeugung
    1.11
     últimos
    1.11
    Activations Density 0.135%

    No Known Activations