© 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. 59193
    Prev
    Next
    INDEX
    Explanations

    international field contexts

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

    The neuron detects mentions of international or global contexts (e.g. “international,” “global,” “internationalization,” 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
    嗶
    -1.28
     помогают
    -1.24
     centru
    -1.24
     помогут
    -1.22
    あげて
    -1.20
     duidelijk
    -1.20
     Algunos
    -1.20
    ⑉
    -1.16
     such
    -1.16
     untersucht
    -1.16
    POSITIVE LOGITS
    🌎
    1.34
    观的
    1.28
    tintColor
    1.21
    (
    1.16
    </u>
    1.15
    %
    1.11
     penyer
    1.10
     Tugend
    1.10
     опыта
    1.09
     yog
    1.08
    Activations Density 0.057%

    No Known Activations