© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32357
    Prev
    Next
    INDEX
    Explanations

    `and`, `absolute`, `cookie`, `un`, `the`

    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_34/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
     Afghanistan
    -0.91
    秣
    -0.82
     Afghan
    -0.81
     Pipeline
    -0.79
     Bois
    -0.78
    西藏
    -0.77
    waard
    -0.77
    Merk
    -0.76
     Cartier
    -0.76
    __);
    -0.73
    POSITIVE LOGITS
    桂
    0.85
     Ninh
    0.73
     kar
    0.69
     perchè
    0.69
    漓
    0.68
    витие
    0.68
    GBR
    0.67
    Firstly
    0.66
     Joplin
    0.66
    냄
    0.66
    Activations Density 0.012%

    No Known Activations