© 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. 22-GEMMASCOPE-RES-131K
    7. 40061
    Prev
    Next
    INDEX
    Explanations

    launch or feed-forward

    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_22/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
    .")]
    -0.96
    unduh
    -0.96
    
    -0.92
    ❢
    -0.89
    ',['
    -0.88
    müş
    -0.84
    delig
    -0.84
    asons
    -0.82
     Attra
    -0.81
    vás
    -0.81
    POSITIVE LOGITS
    )$\\
    0.82
     cuantas
    0.78
    说明
    0.77
    Industries
    0.77
    ghua
    0.75
     tính
    0.72
     AMR
    0.72
    Owned
    0.72
     wrze
    0.71
     تاریخی
    0.71
    Activations Density 0.187%

    No Known Activations