© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10582
    Prev
    Next
    INDEX
    Explanations

    `<param` elements

    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
    ’，
    -1.90
     וג
    -1.88
    歿
    -1.86
    はコチラ
    -1.78
    儿的
    -1.77
    Aujourd
    -1.76
     також
    -1.76
    是我们
    -1.75
     jugado
    -1.75
     transformar
    -1.73
    POSITIVE LOGITS
    1
    2.41
     что
    2.06
    K
    2.02
     $
    1.99
     That
    1.98
    </h3>
    1.92
    \
    1.90
    T
    1.86
    3
    1.86
    L
    1.81
    Activations Density 0.001%

    No Known Activations