© 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. 9291
    Prev
    Next
    INDEX
    Explanations

    code syntax and programming constructs

    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
    氛
    -2.23
     ambayo
    -2.23
    焿
    -2.13
    푣
    -2.05
     Bedürfn
    -2.03
    *
    -1.99
    といっても
    -1.94
    もしくは
    -1.93
    i
    -1.92
    )
    -1.90
    POSITIVE LOGITS
    ྵ
    2.66
    
    2.63
    </sub>
    2.53
    有很多
    2.47
    大约
    2.42
    ления
    2.42
    蕻
    2.41
    </h3>
    2.39
    oughby
    2.38
    ；
    2.23
    Activations Density 0.004%

    No Known Activations