© 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. 120516
    Prev
    Next
    INDEX
    Explanations

    certain number is associated

    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
     each
    -0.07
     readily
    -0.07
    每一個
    -0.06
    যেমন
    -0.06
     각각
    -0.06
     jeweils
    -0.06
    スケジュール
    -0.06
     PKC
    -0.06
     jeweiligen
    -0.06
     항상
    -0.06
    POSITIVE LOGITS
    timezone
    0.07
     parti
    0.07
    random
    0.07
     বিভাগের
    0.06
     партия
    0.06
     وكان
    0.06
     встречаются
    0.06
    roweak
    0.06
    antic
    0.06
    amb
    0.06
    Activations Density 0.050%

    No Known Activations