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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130987
    Prev
    Next
    INDEX
    Explanations

    in

    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
     তথ্য
    -0.06
    palindrome
    -0.05
     информация
    -0.05
    replaceable
    -0.05
    oglobulin
    -0.05
    apis
    -0.05
     communication
    -0.05
    屉
    -0.05
     amy
    -0.05
     Kommunikation
    -0.05
    POSITIVE LOGITS
     সমাধানের
    0.07
     動
    0.07
    佽
    0.07
     лучших
    0.06
    Toward
    0.06
     Considerable
    0.06
    可以在
    0.06
     optimal
    0.06
     ismert
    0.06
     좋을
    0.06
    Activations Density 0.016%

    No Known Activations