© 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. 34-GEMMASCOPE-RES-131K
    7. 64124
    Prev
    Next
    INDEX
    Explanations

    file paths with user names

    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
     helplessness
    -0.94
    makeConstraints
    -0.87
     sofá
    -0.85
    襖
    -0.84
     earnestness
    -0.84
     kutu
    -0.82
    اصمة
    -0.82
     năm
    -0.81
     when
    -0.81
    juin
    -0.81
    POSITIVE LOGITS
     Administrator
    1.61
     user
    1.54
     owner
    1.40
     Owner
    1.36
     PC
    1.34
     admin
    1.34
     administrator
    1.33
    Owner
    1.32
    user
    1.31
    admin
    1.27
    Activations Density 0.006%

    No Known Activations