© 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. 116420
    Prev
    Next
    INDEX
    Explanations

    count or quantity

    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
    暖かい
    -0.06
     cheerfully
    -0.06
    ไทย
    -0.06
     വിവര
    -0.06
     thoroughly
    -0.06
     speedily
    -0.06
    攻略
    -0.06
     começo
    -0.06
     wilfully
    -0.06
     encuentra
    -0.06
    POSITIVE LOGITS
     required
    0.07
     needed
    0.06
     उठ
    0.06
     нужна
    0.06
    起床
    0.06
    5
    0.06
     требу
    0.06
     desired
    0.05
     ..
    0.05
     фигу
    0.05
    Activations Density 0.001%

    No Known Activations