© 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. 45652
    Prev
    Next
    INDEX
    Explanations

    background color codes

    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
     mágica
    -0.75
    Ditto
    -0.75
    harf
    -0.73
    爷
    -0.72
    ruby
    -0.71
    orges
    -0.71
     przysz
    -0.71
    Cocoa
    -0.70
     النار
    -0.70
    amoja
    -0.69
    POSITIVE LOGITS
     background
    1.82
    background
    1.70
     white
    1.65
     Background
    1.62
    Background
    1.55
    WHITE
    1.53
    white
    1.48
    BACKGROUND
    1.46
     backgrounds
    1.41
    背景
    1.36
    Activations Density 0.011%

    No Known Activations