© 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. 116234
    Prev
    Next
    INDEX
    Explanations

    select distinct or unique

    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
     puisqu
    -0.07
     certaines
    -0.06
    nul
    -0.06
     inú
    -0.06
     многочис
    -0.05
     duplic
    -0.05
     kolem
    -0.05
     prese
    -0.05
    ¹.
    -0.05
     ratus
    -0.05
    POSITIVE LOGITS
     யார்
    0.07
    Suggest
    0.06
     why
    0.06
     transición
    0.06
     ouro
    0.06
     how
    0.06
    खुद
    0.06
    
    0.06
     दौरान
    0.06
     पुत्री
    0.06
    Activations Density 0.002%

    No Known Activations