© 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. 120273
    Prev
    Next
    INDEX
    Explanations

    legal documents or names

    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
     lepiej
    -0.06
    สะดวก
    -0.06
    ポケット
    -0.06
    新
    -0.06
    Pued
    -0.06
     souvent
    -0.06
     niewiel
    -0.06
     Pocket
    -0.06
     rápid
    -0.05
     নিশ্চ
    -0.05
    POSITIVE LOGITS
     엄청
    0.07
     tento
    0.06
     没有
    0.06
     प्रतियोगिता
    0.06
    .......
    0.06
     अन्य
    0.06
     concept
    0.06
    Qaeda
    0.06
     verifica
    0.06
     ஒரு
    0.06
    Activations Density 0.002%

    No Known Activations