© 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. 71506
    Prev
    Next
    INDEX
    Explanations

    judicial confirmations and nominations

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

    The neuron is triggered by capitalized proper names and formal titles, especially those of judges or high‐profile individuals (e.g. Supreme Court nominees).

    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
     legais
    -1.40
    ׇ
    -1.31
     चीज़
    -1.30
     Vuelta
    -1.26
     essentiel
    -1.25
     Toutes
    -1.25
     Règlement
    -1.25
     verboten
    -1.25
     autocollant
    -1.25
    humidité
    -1.19
    POSITIVE LOGITS
    ַּ
    1.36
     his
    1.36
    ִּ
    1.30
    ӧ
    1.25
     için
    1.19
    jí
    1.18
     glück
    1.16
    וּ
    1.16
     candidate
    1.14
     who
    1.13
    Activations Density 0.033%

    No Known Activations