© 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. 119183
    Prev
    Next
    INDEX
    Explanations

    This phenomenon may

    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
    enough
    -0.06
    ge
    -0.06
     মহান
    -0.06
    Some
    -0.05
     বলেছিল
    -0.05
     মনের
    -0.05
    ibe
    -0.05
    cyber
    -0.05
    fan
    -0.05
    some
    -0.05
    POSITIVE LOGITS
    大切な
    0.07
    確実に
    0.06
     ну
    0.06
    明らかに
    0.06
    氀
    0.06
     лучшие
    0.06
     Contributing
    0.06
     unwa
    0.06
    Important
    0.06
     хорошие
    0.06
    Activations Density 0.009%

    No Known Activations