© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73111
    Prev
    Next
    INDEX
    Explanations

    years of experience

    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
     there
    -1.74
    {
    -1.66
     There
    -1.64
    .
    -1.62
     you
    -1.55
    なども
    -1.43
    的時候
    -1.42
     most
    -1.41
     igreja
    -1.41
    するので
    -1.38
    POSITIVE LOGITS
     of
    1.79
     improvement
    1.50
     nee
    1.46
     assurance
    1.43
     <>",
    1.41
     arti
    1.36
     فرمان
    1.30
     Variante
    1.30
    』（
    1.29
    })()
    1.28
    Activations Density 0.044%

    No Known Activations