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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129070
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on words and phrases that signal ranking or ordering contexts—terms like “ranking,” “table,” “top,” “score,” and similar.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    ranking and order

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ↵↵
    -1.10
    亭
    -1.02
     work
    -1.01
     can
    -0.98
    学者
    -0.94
     við
    -0.94
     when
    -0.93
     cycle
    -0.91
    了
    -0.91
        
    -0.90
    POSITIVE LOGITS
     rankings
    1.48
     ranking
    1.34
     ranked
    1.23
     classement
    1.21
    dismo
    1.18
    descending
    1.15
    Ranking
    1.06
    tanaman
    1.04
    coconut
    1.03
     mikrofon
    1.03
    Activations Density 0.048%

    No Known Activations