© 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. 1604
    Prev
    Next
    INDEX
    Explanations

    code directives and definitions

    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
     gh
    -1.00
    \\
    -1.00
     uska
    -0.94
     鲜
    -0.92
     lượt
    -0.91
    าสตร์
    -0.91
     ''){
    -0.90
    bited
    -0.90
     aktuelle
    -0.90
    eds
    -0.90
    POSITIVE LOGITS
     cipolla
    1.16
     proporcionan
    1.13
     ayudan
    1.05
     utilizan
    0.99
     generan
    0.97
    Antal
    0.95
    näm
    0.95
    توضیحات
    0.95
     piensan
    0.95
    Tentang
    0.94
    Activations Density 0.025%

    No Known Activations