© 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. 22-GEMMASCOPE-RES-131K
    7. 28176
    Prev
    Next
    INDEX
    Explanations

    although contrasting phrases

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

    The neuron detects XML‐related annotation identifiers (e.g. XmlElement, XmlAttribute, XmlSchema) 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_22/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
     fhew
    -1.48
    퐹
    -1.40
     marea
    -1.39
    </sup>
    -1.38
     fhould
    -1.32
     obfer
    -1.31
    却被
    -1.29
     唯美
    -1.27
     vapore
    -1.27
    a
    -1.27
    POSITIVE LOGITS
    vantaged
    1.44
     möchten
    1.32
     extremadamente
    1.31
     únicamente
    1.30
     juzg
    1.27
     recientemente
    1.24
     поэтому
    1.23
     enseñ
    1.22
     prácticamente
    1.21
     ligeramente
    1.21
    Activations Density 0.001%

    No Known Activations