© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130228
    Prev
    Next
    INDEX
    Explanations

    modelmicrocontroller model numbers and prefixes

    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
     pioneered
    -0.06
     específicos
    -0.06
     improved
    -0.06
    carried
    -0.06
     selalu
    -0.06
     carried
    -0.06
     patents
    -0.06
     hatta
    -0.06
     Improved
    -0.06
     eran
    -0.06
    POSITIVE LOGITS
     खेल
    0.08
     ಅವಕಾಶ
    0.06
     민
    0.06
     五
    0.06
     playable
    0.06
     Игра
    0.06
    四十
    0.06
    ąda
    0.06
    五十
    0.06
    不起
    0.05
    Activations Density 0.002%

    No Known Activations