© 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. 117808
    Prev
    Next
    INDEX
    Explanations

    label, input, two fields

    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
     형태
    -0.07
    EXTERNAL
    -0.07
     quiera
    -0.06
    都合
    -0.06
     完成
    -0.06
     хоче
    -0.06
     ফর্ম
    -0.06
    uthers
    -0.06
     Где
    -0.06
     ঠিকানা
    -0.06
    POSITIVE LOGITS
     গিয়েছিলাম
    0.06
     similar
    0.06
    aun
    0.06
     অমন
    0.06
    WARN
    0.06
    ;:
    0.06
    similar
    0.06
     similarly
    0.06
     support
    0.06
     ურთიერთ
    0.06
    Activations Density 0.009%

    No Known Activations