© 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. 65393
    Prev
    Next
    INDEX
    Explanations

    layering clothing

    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
     کنید
    -0.83
     لص
    -0.76
    ناة
    -0.73
    resourceId
    -0.73
     auteur
    -0.70
     caer
    -0.69
     பொ
    -0.69
     PBX
    -0.69
    FromJson
    -0.69
     Clovis
    -0.68
    POSITIVE LOGITS
     layer
    1.80
     layers
    1.70
     layering
    1.68
    layer
    1.52
    Layer
    1.40
     Layer
    1.36
    layers
    1.32
    Layers
    1.28
     Layers
    1.20
    LAYER
    1.19
    Activations Density 0.017%

    No Known Activations