© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14628
    Prev
    Next
    INDEX
    Explanations

    javascript object properties

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

    This neuron activates on occurrences of the “prototype” property access in code.

    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
     asegura
    -1.95
     pierwszej
    -1.88
     conférences
    -1.72
     cambió
    -1.71
     continúas
    -1.71
     žiad
    -1.70
     nouveautés
    -1.69
    锃
    -1.69
     ofrecen
    -1.68
     głównie
    -1.68
    POSITIVE LOGITS
    </h2>
    2.69
    S
    2.05
     not
    1.96
    B
    1.86
     three
    1.78
     using
    1.78
     take
    1.77
     two
    1.70
    R
    1.69
    とはいえ
    1.68
    Activations Density 0.001%

    No Known Activations