© 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. 120462
    Prev
    Next
    INDEX
    Explanations

    genome sequences

    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
    unjukkan
    -0.07
     groups
    -0.07
     بیگ
    -0.06
     gruppi
    -0.06
     Groups
    -0.06
     bookArray
    -0.06
     chiama
    -0.06
     रोडवेज
    -0.06
     các
    -0.06
    มอง
    -0.06
    POSITIVE LOGITS
     completely
    0.06
    作为一个
    0.06
     as
    0.06
    一个
    0.06
     solidar
    0.06
    ,
    0.06
     नैसर्गिक
    0.06
     terrible
    0.06
     FULL
    0.06
     awful
    0.06
    Activations Density 0.012%

    No Known Activations