© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66648
    Prev
    Next
    INDEX
    Explanations

    operations

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

    The neuron fires on the substring “ops,” i.e. identifiers or words containing “ops.”

    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
    '
    -3.11
    淠
    -3.05
    尛
    -2.95
    蒟
    -2.81
    雠
    -2.63
    <bos>
    -2.61
     emporio
    -2.61
    翾
    -2.56
     televis
    -2.50
    蕺
    -2.50
    POSITIVE LOGITS
    𖣘
    3.20
    秾
    3.00
     masih
    2.52
     dasarnya
    2.52
    喾
    2.38
     crumble
    2.36
    ꜆
    2.36
     smitten
    2.33
     ops
    2.28
     yearn
    2.28
    Activations Density 0.004%

    No Known Activations