© 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. 84371
    Prev
    Next
    INDEX
    Explanations

    API path URLs

    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
    ϴ
    -0.92
     atlet
    -0.90
     Pintura
    -0.84
     stik
    -0.83
     valentino
    -0.83
     eksklu
    -0.82
    wingen
    -0.82
     burberry
    -0.80
     Filipinos
    -0.80
     MAIS
    -0.78
    POSITIVE LOGITS
     path
    1.09
     trail
    0.82
    path
    0.79
     zast
    0.79
     deleteById
    0.79
    replaceAll
    0.77
    itch
    0.77
     route
    0.76
     ser
    0.75
    pretrained
    0.75
    Activations Density 0.002%

    No Known Activations