© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42020
    Prev
    Next
    INDEX
    Explanations

    xml key-value pairs

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

    The neuron fires on Apple plist `<key>` entries—particularly CFBundle* property names in XML property lists.

    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
    也很
    -1.34
     porque
    -1.23
     we
    -1.23
    栳
    -1.20
     confirmar
    -1.19
    çoit
    -1.17
     outputStream
    -1.17
     косме
    -1.16
    })}$
    -1.15
     naszych
    -1.13
    POSITIVE LOGITS
     only
    1.45
    了一会儿
    1.41
     atractiva
    1.29
     hadapan
    1.27
    危險
    1.24
    暈
    1.22
    isiin
    1.21
     zowel
    1.20
     by
    1.20
     just
    1.20
    Activations Density 0.134%

    No Known Activations