© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129177
    Prev
    Next
    INDEX
    Explanations

    Civil Action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aer
    -0.07
     Interpre
    -0.06
     Aer
    -0.06
    /
    -0.06
    ">{
    -0.06
     টেলিভিশ
    -0.06
    まず
    -0.06
     eventuali
    -0.06
     ultimately
    -0.06
     началом
    -0.06
    POSITIVE LOGITS
    Filename
    0.07
       
    0.06
     HEIGHT
    0.06
     one
    0.06
    とても
    0.06
     väldigt
    0.06
     ძალიან
    0.06
    被称为
    0.05
    codename
    0.05
     Joseph
    0.05
    Activations Density 0.003%

    No Known Activations