© 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. 104401
    Prev
    Next
    INDEX
    Explanations

    durations in years

    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
    }$
    -1.54
    </b>
    -1.50
    iyaki
    -1.48
     it
    -1.41
    </h4>
    -1.38
    </h2>
    -1.38
    </sup>
    -1.34
    {
    -1.30
     дюй
    -1.30
     {
    
    
    -1.28
    POSITIVE LOGITS
    tischer
    1.54
     deine
    1.35
     لاح
    1.28
    した
    1.27
    cents
    1.20
     bande
    1.19
    ggars
    1.19
    對
    1.16
    вом
    1.16
     особли
    1.15
    Activations Density 0.006%

    No Known Activations