© 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. 129233
    Prev
    Next
    INDEX
    Explanations

    ball rolls; curved path; volume; speed; Q:

    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
     நிலைய
    -0.07
    where
    -0.06
     استاد
    -0.06
     if
    -0.06
     where
    -0.06
    पना
    -0.06
     estabele
    -0.06
     situação
    -0.06
     widths
    -0.05
     problém
    -0.05
    POSITIVE LOGITS
     lipids
    0.06
     polymer
    0.06
     രണ്ട്
    0.06
     released
    0.06
     tanul
    0.06
     hydration
    0.06
     tweaks
    0.06
     polymers
    0.06
     Gameplay
    0.06
     আলাদা
    0.06
    Activations Density 0.001%

    No Known Activations