© 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. 44264
    Prev
    Next
    INDEX
    Explanations

    Top 10 lists

    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
     สำหรับ
    -1.73
    }
    -1.71
    𝄆
    -1.69
     มัน
    -1.67
    
    -1.66
     {
    -1.65
     การ
    -1.64
    ↵↵
    -1.64
    考虑到
    -1.60
    馓
    -1.60
    POSITIVE LOGITS
     of
    2.42
     this
    1.95
     for
    1.81
     вересня
    1.77
    ็น
    1.77
     置物
    1.73
     січня
    1.67
     homicidio
    1.66
     változ
    1.62
    just
    1.61
    Activations Density 0.008%

    No Known Activations