© 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. 116913
    Prev
    Next
    INDEX
    Explanations

    ment, disease, satchel

    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
    amethasone
    -0.07
    这不是
    -0.06
    ام
    -0.06
     sieht
    -0.06
     multiple
    -0.06
     تخ
    -0.06
     danas
    -0.06
     longo
    -0.06
     incontro
    -0.06
     Bunun
    -0.06
    POSITIVE LOGITS
     provoke
    0.06
    क़
    0.06
     প্রতিষ্ঠিত
    0.05
    кви
    0.05
    érie
    0.05
     tuin
    0.05
     Poultry
    0.05
     njen
    0.05
    kości
    0.05
    urban
    0.05
    Activations Density 0.009%

    No Known Activations