© 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. 23568
    Prev
    Next
    INDEX
    Explanations

    system call prefixes

    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
     pié
    -0.90
     chaus
    -0.89
     repens
    -0.85
    -0.85
     renk
    -0.85
     indirec
    -0.85
     senin
    -0.85
     pantalon
    -0.84
    啃
    -0.84
     renon
    -0.83
    POSITIVE LOGITS
    這裡
    0.93
     to
    0.91
     aproape
    0.87
     yesterday
    0.85
     here
    0.83
     as
    0.82
     today
    0.81
     when
    0.81
     almost
    0.79
    บ้าน
    0.78
    Activations Density 0.000%

    No Known Activations