© 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. 119742
    Prev
    Next
    INDEX
    Explanations

    comments and code headers

    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
     interacting
    -0.07
    interacting
    -0.06
    -
    -0.06
     minta
    -0.06
    第七
    -0.06
    是否有
    -0.06
    滑
    -0.06
     reacciones
    -0.06
     reacting
    -0.06
     Thirdly
    -0.06
    POSITIVE LOGITS
     plutôt
    0.06
     avantage
    0.06
    iteli
    0.06
     ноябре
    0.06
    দ্দি
    0.06
     سلسلہ
    0.06
     pedigree
    0.05
     কষ্ট
    0.05
     chứ
    0.05
    ZP
    0.05
    Activations Density 0.012%

    No Known Activations