© 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. 10-GEMMASCOPE-RES-131K
    7. 47693
    Prev
    Next
    INDEX
    Explanations

    creative work attributions

    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_10/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
    ).
    -2.44
     for
    -2.38
    {
    -2.34
    ;
    -2.27
    ,&
    -2.23
     in
    -2.19
    m
    -2.14
    %
    -2.13
    AndPassword
    -2.00
    lysm
    -2.00
    POSITIVE LOGITS
          
    2.41
     "
    2.19
    很好的
    2.14
    Estás
    2.05
    我们可以
    2.05
     ทั้ง
    2.03
     спросил
    2.02
     Suiza
    2.02
     sker
    2.02
     skrev
    2.00
    Activations Density 0.002%

    No Known Activations