© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130446
    Prev
    Next
    INDEX
    Explanations

    specific biological markers and proteins

    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
     weiteres
    -0.07
     robust
    -0.07
     noteworthy
    -0.06
    toadd
    -0.06
    Super
    -0.06
     intriguing
    -0.06
     CHURCH
    -0.06
     combinaison
    -0.06
    价值
    -0.06
     distressed
    -0.06
    POSITIVE LOGITS
    各个
    0.07
     обычной
    0.06
     বারবার
    0.06
     daily
    0.06
    ,【
    0.06
     स्वयं
    0.06
    daily
    0.06
     각
    0.06
     própria
    0.06
     Artinya
    0.06
    Activations Density 0.005%

    No Known Activations