© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 57465
    Prev
    Next
    INDEX
    Explanations

    plot overview

    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
    vantaged
    -3.30
    wiście
    -2.78
     alcool
    -2.73
    
    -2.66
     brillant
    -2.59
     devine
    -2.58
    
    -2.58
     restau
    -2.56
     signes
    -2.50
    鹟
    -2.47
    POSITIVE LOGITS
    '
    3.25
    </strong>
    3.20
    </h3>
    3.19
    -
    3.17
    可以
    3.14
     可以
    2.66
     freaking
    2.61
    他的
    2.58
    1
    2.56
    \
    2.56
    Activations Density 0.015%

    No Known Activations