© 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. 120620
    Prev
    Next
    INDEX
    Explanations

    binding protein

    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
     dubious
    -0.06
    空
    -0.06
     aerobic
    -0.06
     మొద
    -0.06
    consum
    -0.06
     ያል
    -0.06
     consumes
    -0.06
     относи
    -0.06
     Weak
    -0.06
     questionable
    -0.06
    POSITIVE LOGITS
     अत्यधिक
    0.06
     наші
    0.06
    changed
    0.06
    chunk
    0.06
     geändert
    0.06
     tyto
    0.06
     changed
    0.06
    prestations
    0.06
    这些
    0.06
    previously
    0.06
    Activations Density 0.010%

    No Known Activations