© 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. 10-GEMMASCOPE-RES-131K
    4. 110707
    Prev
    Next
    INDEX
    Explanations

    demo examples

    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_10/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
    
    -1.98
    ⟝
    -1.84
     NACIONAL
    -1.83
    imageshack
    -1.82
    IANGLES
    -1.80
     prepares
    -1.78
     That
    -1.77
    ある
    -1.73
    blurRadius
    -1.73
    ificaciones
    -1.70
    POSITIVE LOGITS
    0
    2.75
    .
    2.63
    M
    2.20
    [
    2.17
    u
    2.02
    (
    1.96
     disiplin
    1.90
    _
    1.90
    <
    1.88
     وجود
    1.85
    Activations Density 0.003%

    No Known Activations