© 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. 84691
    Prev
    Next
    INDEX
    Explanations

    nonetheless introducing contrast

    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
    鈇
    -2.88
    嵙
    -2.70
    毉
    -2.70
    蟥
    -2.56
    ⃙
    -2.56
    觏
    -2.55
    嫱
    -2.53
    釭
    -2.48
    繻
    -2.48
    ',
    -2.44
    POSITIVE LOGITS
     ,‬
    2.91
    vantaged
    2.64
    ↵
    2.55
    蓥
    2.53
     يش
    2.47
    其妙
    2.44
    菪
    2.42
    就像是
    2.38
    sedown
    2.36
     fragte
    2.36
    Activations Density 0.000%

    No Known Activations