© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95577
    Prev
    Next
    INDEX
    Explanations

    opposition and intervention

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

    The neuron activates on mentions of countries or major Western political entities (e.g. France, the European Union, “Western”) and their policy stances.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Metode
    -1.30
     Karakter
    -1.23
     många
    -1.15
     benzin
    -1.12
     ciasc
    -1.12
     Belajar
    -1.06
     الشاشة
    -1.05
    abonnement
    -1.05
    poran
    -1.04
    reiches
    -1.04
    POSITIVE LOGITS
     support
    1.38
    ֶּ
    1.19
     تصریح
    1.16
     its
    1.13
    ַּ
    1.13
     itself
    1.12
    وضوع
    1.12
     intervention
    1.11
     aid
    1.10
    upport
    1.10
    Activations Density 0.040%

    No Known Activations