© 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. 118998
    Prev
    Next
    INDEX
    Explanations

    code and configuration files

    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
     akár
    -0.06
     পাঁ
    -0.06
    !
    -0.06
     description
    -0.06
     lookup
    -0.06
     $
    -0.06
    rebbero
    -0.06
     mullet
    -0.06
     sensiblement
    -0.06
    নব
    -0.06
    POSITIVE LOGITS
    时间
    0.07
     time
    0.06
     antiviral
    0.06
    🔸
    0.06
     উত্তরা
    0.06
     ETFs
    0.06
     اين
    0.06
     ಕನ್ನಡ
    0.06
     время
    0.06
    orems
    0.06
    Activations Density 0.005%

    No Known Activations