© 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. 90519
    Prev
    Next
    INDEX
    Explanations

    subject followed by do

    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
     olmayan
    -0.92
     tiež
    -0.81
     teléfonos
    -0.80
    คือ
    -0.77
     estas
    -0.77
    .}(
    -0.75
    это
    -0.75
    adalah
    -0.73
     pozw
    -0.73
    lerle
    -0.73
    POSITIVE LOGITS
     does
    5.69
     do
    5.50
    Does
    3.75
    does
    3.59
     Does
    3.30
     did
    3.25
    do
    2.80
    Do
    2.47
     DOES
    2.38
     doe
    2.38
    Activations Density 0.096%

    No Known Activations