© 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. 121041
    Prev
    Next
    INDEX
    Explanations

    and claims, herein, matter, invention

    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
    目前的
    -0.06
     最高
    -0.06
    ivably
    -0.06
    磯
    -0.06
     axial
    -0.06
     नेटवर्क
    -0.06
     masih
    -0.06
     realistic
    -0.05
     it
    -0.05
     bereits
    -0.05
    POSITIVE LOGITS
     Salvation
    0.06
    neh
    0.06
    ໂດຍ
    0.06
    都
    0.06
     people
    0.06
     fleet
    0.06
    oxygen
    0.05
     volcanic
    0.05
    都是
    0.05
     are
    0.05
    Activations Density 0.004%

    No Known Activations