© 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. 34-GEMMASCOPE-RES-131K
    7. 73766
    Prev
    Next
    INDEX
    Explanations

    column names and types

    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
    étro
    -0.97
    ujem
    -0.95
    angkap
    -0.91
    お楽しみに
    -0.90
     {...
    -0.90
    posizioni
    -0.88
    　↓
    -0.85
    Collegamenti
    -0.85
    roaches
    -0.85
    দ্ধ
    -0.85
    POSITIVE LOGITS
     name
    1.38
     Name
    1.07
     named
    1.06
    name
    1.05
     имени
    1.03
     tên
    1.01
     называется
    0.95
    ByName
    0.92
    名前
    0.92
     название
    0.89
    Activations Density 0.001%

    No Known Activations