© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102582
    Prev
    Next
    INDEX
    Explanations

    code comments and boilerplate

    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
     so
    -1.15
     its
    -1.04
     all
    -1.00
     both
    -0.94
     helping
    -0.87
     tutti
    -0.85
     hoping
    -0.84
     promote
    -0.82
     as
    -0.81
     any
    -0.81
    POSITIVE LOGITS
    line
    0.90
    ddress
    0.89
     commendation
    0.87
    paquete
    0.87
     olabilir
    0.86
    printLine
    0.85
    Fiz
    0.84
    캬
    0.84
     ざ
    0.84
    அ
    0.82
    Activations Density 0.001%

    No Known Activations