© 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. 28646
    Prev
    Next
    INDEX
    Explanations

    Association of, To link, Our goal

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find the specific term “advantage.”

    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
    diğinde
    -1.21
    くださいませ
    -1.17
     рестай
    -1.10
     "}";
    -1.07
    ının
    -1.05
     LayoutInflater
    -1.01
    hålla
    -1.01
     merasakan
    -1.00
    いただけます
    -0.99
     QtCore
    -0.99
    POSITIVE LOGITS
    sre
    1.15
     multiuso
    1.05
     フォント
    1.00
     poliuret
    0.99
    쁘
    0.97
     especially
    0.96
     poliester
    0.96
     specif
    0.95
     prema
    0.94
     particularly
    0.93
    Activations Density 0.000%

    No Known Activations