© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128421
    Prev
    Next
    INDEX
    Explanations

    integrated circuit

    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
    Not in Any Lists

    No Comments

    Negative Logits
     πραγμα
    -0.07
     hingga
    -0.07
     реально
    -0.07
     désormais
    -0.07
     stvarn
    -0.07
    截至
    -0.07
     উপনিবেশ
    -0.07
     weder
    -0.07
     ocho
    -0.06
     réellement
    -0.06
    POSITIVE LOGITS
     justement
    0.05
     JUST
    0.05
     magyar
    0.05
     முன்னர்
    0.05
    Wine
    0.05
     మరి
    0.05
     മറ
    0.05
    Just
    0.05
    秸
    0.05
    ذية
    0.05
    Activations Density 0.005%

    No Known Activations