© 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. 128668
    Prev
    Next
    INDEX
    Explanations

    * : ____________

    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
     ज़िंदगी
    -0.06
    订单
    -0.06
     provide
    -0.06
    全部
    -0.06
     purch
    -0.06
     επισ
    -0.06
     অনেকটাই
    -0.06
    ạm
    -0.06
     Интере
    -0.06
     फॉर्म
    -0.06
    POSITIVE LOGITS
     and
    0.07
     whose
    0.07
     following
    0.06
    腔
    0.06
    :
    0.06
     urmă
    0.06
     siguiente
    0.06
     kemudian
    0.06
    ____________
    0.06
     erforderlich
    0.06
    Activations Density 0.004%

    No Known Activations