© 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. 32870
    Prev
    Next
    INDEX
    Explanations

    numbers and integer elements

    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
     cerchi
    -0.83
     fecha
    -0.79
    ционной
    -0.78
     adored
    -0.77
    umont
    -0.75
    سلام
    -0.75
     molta
    -0.75
    Bakgrunnsstoff
    -0.73
    wegen
    -0.73
     Bege
    -0.73
    POSITIVE LOGITS
     عناصر
    1.10
     numbers
    1.08
     negative
    1.07
     Negative
    1.02
     odd
    0.96
     elements
    0.95
     positive
    0.91
     Element
    0.90
     element
    0.90
     Numbers
    0.90
    Activations Density 0.061%

    No Known Activations