© 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. 128048
    Prev
    Next
    INDEX
    Explanations

    EDA case numbers

    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
    重新
    -0.06
     what
    -0.06
    maj
    -0.06
    multi
    -0.05
    Jx
    -0.05
    ,
    -0.05
     다시
    -0.05
    ifi
    -0.05
    ona
    -0.05
    ent
    -0.05
    POSITIVE LOGITS
     for
    0.08
     Для
    0.08
     rudimentary
    0.07
     perpetually
    0.07
     для
    0.07
     ridiculously
    0.07
     insanely
    0.07
     facilitates
    0.07
     ludicrous
    0.07
     für
    0.07
    Activations Density 0.002%

    No Known Activations