© 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. 86914
    Prev
    Next
    INDEX
    Explanations

    square root calculations

    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
     kilowatt
    -0.84
     Andro
    -0.82
    зовые
    -0.81
    rittura
    -0.79
     файлы
    -0.77
    Портал
    -0.76
    zucker
    -0.76
    Variance
    -0.76
    grin
    -0.75
    })^{
    -0.75
    POSITIVE LOGITS
    sqrt
    1.00
     sqrt
    0.90
    deos
    0.77
     speed
    0.76
    合成
    0.72
    removeItem
    0.71
    ї
    0.71
     Questions
    0.69
     thrilled
    0.69
    地区
    0.68
    Activations Density 0.024%

    No Known Activations