© 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. 128044
    Prev
    Next
    INDEX
    Explanations

    authoring, creation, and communication

    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
    肿
    -0.06
     तीन
    -0.06
     пяти
    -0.06
     bidder
    -0.06
    izziness
    -0.06
     દવા
    -0.06
    Beschreibung
    -0.06
     மீண்டும்
    -0.06
    ড়াল
    -0.06
    куси
    -0.06
    POSITIVE LOGITS
     initio
    0.07
     Which
    0.07
    情感
    0.06
     initiating
    0.06
     sih
    0.05
    只是
    0.05
     engaging
    0.05
    øy
    0.05
    Which
    0.05
    டல்
    0.05
    Activations Density 0.001%

    No Known Activations