© 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. 117986
    Prev
    Next
    INDEX
    Explanations

    book

    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
     mins
    -0.06
     ব্যতীত
    -0.06
    VIP
    -0.06
     imperfect
    -0.06
    🏘
    -0.06
    ⏯
    -0.05
    Neither
    -0.05
    さと
    -0.05
    🗻
    -0.05
     видом
    -0.05
    POSITIVE LOGITS
     inoltre
    0.07
    became
    0.07
     außerdem
    0.07
     kullanım
    0.06
     influential
    0.06
     उनकी
    0.06
     sone
    0.06
     terkenal
    0.06
     聞
    0.06
    TestMethod
    0.06
    Activations Density 0.025%

    No Known Activations