© 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. 22-GEMMASCOPE-RES-131K
    4. 79617
    Prev
    Next
    INDEX
    Explanations

    sorting or ranking

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

    The neuron activates on terms that signal ordering or sorting operations (e.g. “sort,” “by,” “orderBy,” “ranked”).

    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
     needed
    -0.99
     required
    -0.96
    addError
    -0.85
    酔
    -0.82
    也要
    -0.81
    Volatile
    -0.81
    oulli
    -0.81
    ků
    -0.80
     vielä
    -0.80
    >-</
    -0.79
    POSITIVE LOGITS
    lamó
    1.02
     ranking
    1.02
    ленным
    1.01
     ascending
    0.98
     asc
    0.96
    っそ
    0.94
     wcześ
    0.94
     rankings
    0.94
     abbraccio
    0.93
    descending
    0.93
    Activations Density 0.012%

    No Known Activations