© 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. 118322
    Prev
    Next
    INDEX
    Explanations

    start with cur

    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
    靂
    -1.01
     ganze
    -1.00
     glaubte
    -0.98
     Banyak
    -0.91
     eigene
    -0.90
    otro
    -0.84
     Alguns
    -0.83
     Até
    -0.83
     pautas
    -0.82
    allclose
    -0.81
    POSITIVE LOGITS
     cur
    1.52
     Cur
    1.49
     CUR
    1.43
    cur
    1.43
    Cur
    1.29
    CUR
    1.27
     Cura
    1.07
     vitae
    1.06
     curate
    1.04
     Cursor
    1.03
    Activations Density 0.032%

    No Known Activations