© 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. 38937
    Prev
    Next
    INDEX
    Explanations

    one of

    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
    因为他
    -1.62
    *
    -1.55
    るのは
    -1.55
     手绘
    -1.52
     видит
    -1.51
    ضاء
    -1.50
     одном
    -1.49
     cintur
    -1.48
     diversa
    -1.48
     distinta
    -1.48
    POSITIVE LOGITS
     of
    4.59
     its
    1.74
     что
    1.70
    на
    1.59
    mentaux
    1.59
    зация
    1.57
     gdy
    1.52
    ༛
    1.50
     That
    1.50
    maxn
    1.49
    Activations Density 0.063%

    No Known Activations