© 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. 8114
    Prev
    Next
    INDEX
    Explanations

    Linux kernel

    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
    ayaquil
    -1.61
     causado
    -1.59
    e
    -1.52
    러나
    -1.49
     irgend
    -1.48
    ſelves
    -1.45
    錞
    -1.41
     naszej
    -1.41
    ’.
    -1.37
     usual
    -1.36
    POSITIVE LOGITS
    Ꭳ
    1.48
     burrow
    1.46
    
    1.41
    ㅈ
    1.34
     komplette
    1.34
     riuscito
    1.33
    啣
    1.32
    ząc
    1.30
     ments
    1.30
    菜單
    1.30
    Activations Density 0.044%

    No Known Activations