© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130677
    Prev
    Next
    INDEX
    Explanations

    optical modulation and wave phenomena

    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
    etc
    -1.57
     problem
    -1.45
     
    -1.45
     patrie
    -1.41
    
    -1.38
    ⎯
    -1.38
    ⅘
    -1.38
     ряда
    -1.34
     etc
    -1.33
     бампер
    -1.33
    POSITIVE LOGITS
     at
    1.69
     without
    1.68
    ⚕
    1.48
     sulfu
    1.45
     before
    1.44
     sepenuhnya
    1.43
     apapun
    1.42
     with
    1.40
     and
    1.38
    ׇ
    1.38
    Activations Density 0.376%

    No Known Activations