© 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. 66577
    Prev
    Next
    INDEX
    Explanations

    adjective noun pairings

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

    This neuron responds to title‐ or slogan‐style phrases that repeat or pair key words in parallel (e.g. “Good… Good…,” “Great… Great…,” “Healthy… Healthy… Healthy…,” “New City,” etc.).

    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
     både
    -1.34
     devront
    -1.02
     pourront
    -1.02
     hvit
    -1.02
     lomba
    -0.99
     Président
    -0.98
    ibile
    -0.98
     ambassade
    -0.97
     collè
    -0.96
     kommende
    -0.96
    POSITIVE LOGITS
     for
    0.98
     now
    0.91
     边框
    0.90
     カスタム
    0.88
     Stirn
    0.88
     lifelong
    0.87
    Results
    0.87
    location
    0.85
     profound
    0.85
    Жизнь
    0.84
    Activations Density 0.035%

    No Known Activations