© 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. 10-GEMMASCOPE-RES-131K
    7. 20533
    Prev
    Next
    INDEX
    Explanations

    different types or variations

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

    The neuron is tuned to pick out content‐bearing technical or domain‐specific terms (specialized nouns and adjectives) in formal or descriptive text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     deux
    -1.54
     trois
    -1.48
    那些
    -1.45
    atisk
    -1.42
    those
    -1.36
    two
    -1.35
     two
    -1.34
    ishment
    -1.32
     sva
    -1.30
    ?\
    -1.30
    POSITIVE LOGITS
     olika
    2.36
     różnych
    2.16
     different
    2.09
     różne
    1.95
     distintos
    1.88
     různých
    1.88
     diferentes
    1.83
     різних
    1.82
     farklı
    1.77
     разные
    1.77
    Activations Density 0.216%

    No Known Activations