© 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. 115855
    Prev
    Next
    INDEX
    Explanations

    pandas and numpy code

    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
     it
    -0.07
     because
    -0.07
     
    -0.07
     rather
    -0.06
    因为它
    -0.06
     porque
    -0.06
    Desde
    -0.06
    slab
    -0.06
     السبب
    -0.06
     by
    -0.06
    POSITIVE LOGITS
     Wanneer
    0.07
     अर्पित
    0.06
    যখন
    0.06
     मसलन
    0.06
     عزیز
    0.06
     לאחר
    0.06
     Lorsque
    0.06
     ordinarily
    0.06
    सैन
    0.06
    WHEN
    0.06
    Activations Density 0.018%

    No Known Activations