© 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. 130195
    Prev
    Next
    INDEX
    Explanations

    copyright and duplication

    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
     éventuellement
    -0.06
     eventualmente
    -0.06
    oula
    -0.06
     arist
    -0.06
     ねえ
    -0.06
    ্ট
    -0.05
     GPT
    -0.05
     skulle
    -0.05
     incontinence
    -0.05
     Kou
    -0.05
    POSITIVE LOGITS
     sogenannte
    0.06
     ಹಾಗೂ
    0.06
     συγκεκρι
    0.06
     정보
    0.06
    ďaka
    0.06
     Nombre
    0.06
    ข้อมูล
    0.06
     información
    0.06
     hope
    0.06
     sogen
    0.06
    Activations Density 0.001%

    No Known Activations