© 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. 123600
    Prev
    Next
    INDEX
    Explanations

    parts of or for

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

    The neuron activates specifically on the word “parts.”

    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
    '
    -2.83
    0
    -2.36
    $
    -2.30
    1
    -2.28
    蕺
    -2.17
    AÇÃO
    -2.02
     damski
    -1.91
    髡
    -1.91
     這
    -1.89
     trasero
    -1.88
    POSITIVE LOGITS
    ၟ
    2.88
    𖤍
    2.75
    蕻
    2.72
    »,
    2.66
    骢
    2.55
    ሖ
    2.48
     título
    2.41
     ६
    2.39
    érales
    2.39
    udsman
    2.39
    Activations Density 0.008%

    No Known Activations