© 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. 38879
    Prev
    Next
    INDEX
    Explanations

    regulation of industries and society

    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
     verur
    -1.89
    烔
    -1.75
     начинает
    -1.68
     überg
    -1.68
    StoryboardSegue
    -1.67
    ricanes
    -1.65
    脸上的
    -1.61
     You
    -1.61
    mbgg
    -1.54
    idered
    -1.53
    POSITIVE LOGITS
    蛧
    1.84
    IN
    1.77
    ſtra
    1.77
    EN
    1.76
    */
    1.73
    m
    1.72
    ↵
    1.70
     terjadinya
    1.69
     pikir
    1.67
    وفق
    1.65
    Activations Density 0.041%

    No Known Activations