© 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. 129588
    Prev
    Next
    INDEX
    Explanations

    web links and code syntax

    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
     அவரின்
    -0.06
     ۷
    -0.06
    hemia
    -0.06
     succesfully
    -0.06
     وت
    -0.05
    ⟣
    -0.05
     xWidth
    -0.05
     উপকৃত
    -0.05
     Их
    -0.05
     کرتے
    -0.05
    POSITIVE LOGITS
     Massachusetts
    0.06
     types
    0.06
    দিনই
    0.05
     además
    0.05
    用于
    0.05
     feats
    0.05
     thinkers
    0.05
     વિશે
    0.05
     Webin
    0.05
     máme
    0.05
    Activations Density 0.037%

    No Known Activations