© 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. 3819
    Prev
    Next
    INDEX
    Explanations

    code comments and programming language keywords

    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
     anteriores
    -1.45
     devem
    -1.39
     anteriormente
    -1.38
    ResumeLayout
    -1.38
     zustand
    -1.34
     mittlere
    -1.34
    thay
    -1.34
     vayan
    -1.34
    ?,?,
    -1.32
     reducción
    -1.30
    POSITIVE LOGITS
     to
    1.81
    および
    1.56
     indisponible
    1.44
     및
    1.40
     has
    1.38
    及び
    1.38
     may
    1.38
     became
    1.33
     really
    1.30
     valamint
    1.27
    Activations Density 0.092%

    No Known Activations