© 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. 38263
    Prev
    Next
    INDEX
    Explanations

    programming include directives

    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
     other
    -0.98
     every
    -0.94
     edgy
    -0.93
     procedures
    -0.91
    женные
    -0.88
     membayar
    -0.88
     nighttime
    -0.87
    𝑰
    -0.82
    られていた
    -0.82
    しております
    -0.82
    POSITIVE LOGITS
     include
    1.98
    include
    1.81
     includes
    1.56
    包括
    1.41
     incluye
    1.37
     incluem
    1.34
    if
    1.31
     incluyen
    1.30
     inclui
    1.22
    Include
    1.19
    Activations Density 0.071%

    No Known Activations