© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 127925
    Prev
    Next
    INDEX
    Explanations

    code method calls or structure

    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
    Negative Logits
     οπο
    -0.06
     quaisquer
    -0.06
     nouve
    -0.06
     bárm
    -0.06
    就要
    -0.06
     realizzata
    -0.06
     plumber
    -0.06
     creating
    -0.05
     distinctions
    -0.05
     importance
    -0.05
    POSITIVE LOGITS
     очень
    0.06
     ძალიან
    0.06
     দিনের
    0.06
     रिसर्च
    0.06
     rất
    0.06
     생각
    0.06
    Finish
    0.06
     gives
    0.06
     నాలుగు
    0.06
     võivad
    0.06
    Activations Density 0.001%

    No Known Activations