© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7192
    Prev
    Next
    INDEX
    Explanations

    Tony Blair

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

    This neuron specializes in spotting formal institutional or bureaucratic language—terms you’d see in official resolutions, organizational reports, or news‐style announcements.

    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
     онлайн
    -1.23
     stakeholders
    -1.19
     reboot
    -1.14
     timeline
    -1.13
     Odisha
    -1.06
     Ajouter
    -1.02
     LGBT
    -0.99
     Fukushima
    -0.98
     smartphone
    -0.97
     Erdoğan
    -0.97
    POSITIVE LOGITS
     superbly
    1.32
     ибо
    1.24
     timbul
    1.05
     prestigious
    1.03
     lavish
    1.02
     overtly
    1.00
     подчер
    1.00
     genuinely
    0.99
     extraordinarily
    0.98
     presumably
    0.98
    Activations Density 0.035%

    No Known Activations