© 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. 59915
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    </h5>
    -1.66
     was
    -1.56
     is
    -1.48
    ",
    
    -1.48
     my
    -1.39
    》,
    -1.39
     désolés
    -1.38
    蔔
    -1.38
     latter
    -1.35
    </h4>
    -1.34
    POSITIVE LOGITS
    icestershire
    1.41
    Китай
    1.30
    érées
    1.30
     experimentar
    1.23
    erobic
    1.23
     Inggris
    1.20
     Tallinn
    1.18
    נטי
    1.18
    יסט
    1.17
    忉
    1.17
    Activations Density 0.131%

    No Known Activations