© 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. 22-GEMMASCOPE-RES-131K
    4. 104301
    Prev
    Next
    INDEX
    Explanations

    java programming languages and databases

    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_22/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
     in
    -1.43
     before
    -1.32
     or
    -1.27
     should
    -1.20
     when
    -1.09
     intricacies
    -1.09
     started
    -1.07
    
    -1.03
     from
    -1.02
     berapa
    -1.02
    POSITIVE LOGITS
    ons
    1.05
     krótk
    1.03
     دقی
    1.00
     dismantling
    0.99
    比较好
    0.98
     éstos
    0.97
    这些人
    0.97
     やすい
    0.97
    stolic
    0.94
     vsak
    0.94
    Activations Density 0.002%

    No Known Activations