© 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. 117669
    Prev
    Next
    INDEX
    Explanations

    arithmetic sequences

    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
    陋
    -0.06
     क्रिकेटर
    -0.06
     زائد
    -0.06
     यावेळी
    -0.06
     今
    -0.05
    ＋
    -0.05
    elipe
    -0.05
     المزيد
    -0.05
    上述
    -0.05
    ৃতা
    -0.05
    POSITIVE LOGITS
     기존
    0.08
     ಎರ
    0.07
     다른
    0.07
    whole
    0.07
     На
    0.07
     already
    0.06
     whole
    0.06
    ただ
    0.06
     사용할
    0.06
     premium
    0.06
    Activations Density 0.010%

    No Known Activations