© 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. 11611
    Prev
    Next
    INDEX
    Explanations

    translation, id tags

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

    The neuron fires on metadata keys in localization/translation files—e.g. XML `<source>` tags and `msgid` identifiers.

    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
     gewor
    -2.02
     anhänger
    -1.91
    なども
    -1.91
     zubehör
    -1.89
     dando
    -1.88
    -
    -1.85
     électriques
    -1.80
     páns
    -1.80
     elaboración
    -1.78
     fantástica
    -1.77
    POSITIVE LOGITS
    ဴ
    1.98
    }$.
    1.84
     This
    1.83
     appear
    1.78
     при
    1.77
     शुर
    1.76
     receive
    1.74
     indicate
    1.73
    icoot
    1.73
     will
    1.72
    Activations Density 0.002%

    No Known Activations