© 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. 34-GEMMASCOPE-RES-131K
    7. 92114
    Prev
    Next
    INDEX
    Explanations

    metadata labels

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

    This neuron detects metadata field or tag names used in structured data formats (e.g. XML/JSON) such as folder, filename, database, annotation, image, owner, name, source, etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ajajaja
    -1.05
     harta
    -1.05
     salonu
    -1.02
    bedien
    -1.02
    
    -1.01
     hunde
    -1.00
    сная
    -1.00
    suggested
    -0.98
     manier
    -0.94
    parfum
    -0.93
    POSITIVE LOGITS
    ”.
    0.87
    !.
    0.85
     Beur
    0.84
     .”
    0.84
    el
    0.83
    桌上
    0.83
     genau
    0.82
    Appellants
    0.82
    ?.
    0.81
    台上
    0.80
    Activations Density 0.151%

    No Known Activations