© 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. 89977
    Prev
    Next
    INDEX
    Explanations

    context of code elements

    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
     Embar
    -0.86
     celeb
    -0.81
     one
    -0.79
    AndWait
    -0.79
    лго
    -0.78
    Виды
    -0.75
    TextAlignment
    -0.75
     जहां
    -0.74
    最近は
    -0.74
    setStart
    -0.74
    POSITIVE LOGITS
     context
    1.28
     circumstances
    1.20
     contexto
    1.09
    context
    1.00
     contexte
    0.99
     contextos
    0.99
     Context
    0.98
     contesto
    0.98
     already
    0.98
     remaining
    0.91
    Activations Density 0.049%

    No Known Activations