© 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. 8260
    Prev
    Next
    INDEX
    Explanations

    leading or trailing by a margin

    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
     a
    -1.47
    鲠
    -1.45
    those
    -1.45
     szczególnie
    -1.39
     aquellos
    -1.38
     dvě
    -1.35
     tradicionales
    -1.34
    
    -1.29
    瑆
    -1.28
    ឪ
    -1.27
    POSITIVE LOGITS
     intends
    1.63
    to
    1.59
     not
    1.54
    up
    1.45
     than
    1.44
     need
    1.44
    ьем
    1.42
     comunicarse
    1.36
     by
    1.34
    not
    1.33
    Activations Density 0.020%

    No Known Activations