© 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. 34-GEMMASCOPE-RES-131K
    4. 34471
    Prev
    Next
    INDEX
    Explanations

    code comments introducing definitions

    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
     Maintenant
    -0.93
    őzés
    -0.93
    فى
    -0.92
    Еще
    -0.91
    週末
    -0.90
    本日は
    -0.90
    tonsoft
    -0.89
    今日は
    -0.89
     pembe
    -0.87
    RRect
    -0.86
    POSITIVE LOGITS
     define
    2.05
     constants
    1.73
     Define
    1.69
    define
    1.63
    constants
    1.54
    Define
    1.52
     variables
    1.41
     global
    1.41
     defines
    1.35
     definir
    1.35
    Activations Density 0.074%

    No Known Activations