© 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. 130111
    Prev
    Next
    INDEX
    Explanations

    Post Administrator Four Q

    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
    แต่ละ
    -0.07
     jeweiligen
    -0.07
    两侧
    -0.07
    -)
    -0.06
     отдельных
    -0.06
    各
    -0.06
     jeweil
    -0.06
     phía
    -0.06
     each
    -0.06
    밖
    -0.05
    POSITIVE LOGITS
    新たに
    0.06
    Those
    0.06
     ८
    0.06
     newfound
    0.06
     JPG
    0.06
     thoſe
    0.06
    Sarah
    0.06
     Sarah
    0.06
    пута
    0.06
    ätzung
    0.06
    Activations Density 0.001%

    No Known Activations