© 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. 2126
    Prev
    Next
    INDEX
    Explanations

    YAML structure markers

    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
     Bates
    -0.73
     פעם
    -0.73
    スタート
    -0.71
    glise
    -0.71
     много
    -0.70
     روز
    -0.70
     estim
    -0.70
    핀
    -0.68
    线下
    -0.68
    gg
    -0.67
    POSITIVE LOGITS
     Asset
    1.25
    Asset
    1.25
     asset
    1.12
    Selection
    1.06
    asset
    0.96
    serialized
    0.94
     Selection
    0.93
    SELECTION
    0.88
    selection
    0.87
    Neden
    0.82
    Activations Density 0.028%

    No Known Activations