© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130298
    Prev
    Next
    INDEX
    Explanations

    URL path separators

    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
     comprehens
    -0.07
     thorough
    -0.07
     methods
    -0.07
    ansı
    -0.06
     comprehensive
    -0.06
     types
    -0.06
     sets
    -0.06
    types
    -0.06
     correctness
    -0.06
     validity
    -0.06
    POSITIVE LOGITS
     every
    0.06
     
    0.06
     আবাস
    0.06
     there
    0.05
     क्रांतिक
    0.05
     সমাবে
    0.05
     Generic
    0.05
     సందర్భంగా
    0.05
    某
    0.05
     ditt
    0.05
    Activations Density 0.005%

    No Known Activations