© 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. 79708
    Prev
    Next
    INDEX
    Explanations

    elected officials, employers, leaders

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

    The neuron detects mentions of government or civic officials and actions involving contacting or engaging with elected representatives.

    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
     prescriptions
    -0.98
     hybride
    -0.94
     ovale
    -0.93
     poets
    -0.90
    lowed
    -0.89
     tages
    -0.88
    :'/
    -0.88
     TICKET
    -0.88
     éven
    -0.87
     TOPICS
    -0.86
    POSITIVE LOGITS
     musíte
    1.08
     barva
    1.07
     receptive
    1.05
     glaub
    1.02
     mères
    1.00
    ktır
    1.00
     červená
    0.98
    delà
    0.96
     uwagę
    0.96
     reemplazar
    0.96
    Activations Density 0.048%

    No Known Activations