© 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. 120004
    Prev
    Next
    INDEX
    Explanations

    Genes, Cognitive, Q

    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
    quick
    -0.07
     quick
    -0.07
    Quick
    -0.06
     quickly
    -0.06
     रखा
    -0.06
     facilitar
    -0.06
     snel
    -0.06
    quickly
    -0.06
     Quick
    -0.06
    构建
    -0.06
    POSITIVE LOGITS
     before
    0.07
     sebelum
    0.07
    今まで
    0.06
    Sebelum
    0.06
    portions
    0.06
     भारतातील
    0.06
    BEFORE
    0.06
     Jika
    0.06
     eher
    0.06
     vårt
    0.06
    Activations Density 0.001%

    No Known Activations