© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69995
    Prev
    Next
    INDEX
    Explanations

    multi-lingual academic citations

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

    The neuron is sensitive to HTML markup tags (e.g., “<strong>” and “<br/>”).

    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
    缐
    -2.41
    \
    -2.09
                
    -2.02
    ه
    -1.95
    嵛
    -1.93
     icône
    -1.91
    窳
    -1.91
    南浔
    -1.91
     fallu
    -1.86
    ть
    -1.79
    POSITIVE LOGITS
     we
    2.67
     poszczegól
    2.03
    RESULTADOS
    1.95
     have
    1.93
     queste
    1.92
    пыт
    1.88
     necessari
    1.87
    ;;)
    1.85
    these
    1.83
    皛
    1.80
    Activations Density 0.020%

    No Known Activations