© 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. 118747
    Prev
    Next
    INDEX
    Explanations

    money amounts and specific entities

    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
     disagreeable
    -0.06
     adjustment
    -0.06
    ทาง
    -0.06
     suspiciously
    -0.06
     (-)
    -0.06
     শিক্ষার
    -0.06
     petugas
    -0.06
    😢
    -0.05
    ινων
    -0.05
     básicas
    -0.05
    POSITIVE LOGITS
     headlined
    0.06
     আবারও
    0.06
    拍卖
    0.06
     규모
    0.06
     rekind
    0.06
    陆续
    0.06
    規模
    0.06
     forefront
    0.06
     intent
    0.06
    𝗳
    0.06
    Activations Density 0.005%

    No Known Activations