© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43051
    Prev
    Next
    INDEX
    Explanations

    in the making or making of

    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
    </i>
    -1.87
     eléctrico
    -1.80
    ︕
    -1.77
    赑
    -1.70
    \_
    -1.70
     eléctricas
    -1.68
     شدید
    -1.64
    会有
    -1.63
     soportes
    -1.63
     tanques
    -1.62
    POSITIVE LOGITS
     a
    2.28
     véritable
    1.86
     achten
    1.66
     Entste
    1.63
    tiembre
    1.61
    瑒
    1.52
     Männern
    1.52
     akin
    1.51
    .’”
    1.51
    äure
    1.49
    Activations Density 0.013%

    No Known Activations