© 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. 115932
    Prev
    Next
    INDEX
    Explanations

    website links and URLs

    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
     njeg
    -0.07
     NEAR
    -0.07
     tentativo
    -0.06
     되었
    -0.06
    品の
    -0.06
     incidentally
    -0.06
    റായി
    -0.06
    仍
    -0.06
    ‌هایی
    -0.06
     ње
    -0.06
    POSITIVE LOGITS
    หลากหลาย
    0.07
     scalability
    0.06
     நிச்சயம்
    0.06
    _:
    0.06
     komplette
    0.06
     otros
    0.06
     Even
    0.06
     পুরোপুরি
    0.05
    __,
    0.05
     Bahkan
    0.05
    Activations Density 0.005%

    No Known Activations