© 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. 118287
    Prev
    Next
    INDEX
    Explanations

    numbered lists and items

    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
     mehreren
    -0.07
     प्रशिक्
    -0.06
    Qualified
    -0.06
     várias
    -0.06
     প্রশ্ন
    -0.06
     няколко
    -0.06
     with
    -0.06
     δημ
    -0.06
     \&
    -0.06
     મળે
    -0.05
    POSITIVE LOGITS
     aul
    0.06
     science
    0.06
     fantastical
    0.06
    cience
    0.06
    SIBILITIES
    0.06
     housework
    0.06
    äum
    0.06
    uberculosis
    0.06
     الس
    0.06
     kuasa
    0.06
    Activations Density 0.025%

    No Known Activations