© 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. 120457
    Prev
    Next
    INDEX
    Explanations

    size quantities

    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
     вдоль
    -0.06
     उंची
    -0.06
    along
    -0.06
    助于
    -0.06
     along
    -0.06
    ನ್ಯ
    -0.06
    सहाय
    -0.06
     প্রয়
    -0.06
    Have
    -0.06
    地位
    -0.06
    POSITIVE LOGITS
     two
    0.07
    兩
    0.07
    ㎢
    0.06
     zwei
    0.06
    两
    0.06
     until
    0.06
     four
    0.06
     одновременно
    0.06
    squareup
    0.06
     până
    0.06
    Activations Density 0.015%

    No Known Activations