© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 130766
    Prev
    Next
    INDEX
    Explanations

    journal abbreviations followed by a period

    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
     nicely
    -0.07
     bölüm
    -0.06
    上来
    -0.06
    cky
    -0.06
    feedback
    -0.06
     বিষয়টি
    -0.05
     подобных
    -0.05
     خوب
    -0.05
     ইন্দুর
    -0.05
    ジャー
    -0.05
    POSITIVE LOGITS
    ٬
    0.06
     मैच
    0.06
    youtu
    0.06
    ysseus
    0.06
     entrambi
    0.06
     চাষ
    0.06
     održ
    0.06
    Whatever
    0.06
    ᆞ
    0.06
    stens
    0.05
    Activations Density 0.006%

    No Known Activations