© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50240
    Prev
    Next
    INDEX
    Explanations

    programming keywords and possessives

    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
     corporations
    -0.95
    ství
    -0.78
     manager
    -0.77
     corporation
    -0.75
     staples
    -0.75
     Lorsque
    -0.75
     sessions
    -0.74
    iew
    -0.73
    youtube
    -0.73
     факт
    -0.73
    POSITIVE LOGITS
     my
    1.92
    my
    1.16
     our
    0.98
    我的
    0.93
     THE
    0.90
     mijn
    0.90
    the
    0.89
     我的
    0.88
     meine
    0.87
     My
    0.86
    Activations Density 0.247%

    No Known Activations