© 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. 58826
    Prev
    Next
    INDEX
    Explanations

    numbers, quantities, and counting

    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
    Spelling
    -0.71
    ავ
    -0.70
    วัติ
    -0.70
    CONVERT
    -0.69
    Tanks
    -0.67
    푹
    -0.67
    omics
    -0.67
     abbreviations
    -0.66
     obicei
    -0.66
     Paragraph
    -0.66
    POSITIVE LOGITS
     counting
    1.25
     numeral
    1.08
     quantities
    1.05
     quantity
    1.01
    counting
    1.00
    quantity
    0.96
     Counting
    0.94
     مجموعه
    0.91
     numero
    0.91
     colecciones
    0.91
    Activations Density 0.016%

    No Known Activations