© 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. 119629
    Prev
    Next
    INDEX
    Explanations

    Asthma, Economic, Eumitra

    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
     কাঁদতে
    -0.06
     να
    -0.06
     अलावा
    -0.06
     specific
    -0.06
     ہوتے
    -0.06
     सर्किट
    -0.06
     typically
    -0.06
    છ
    -0.06
     ভাবের
    -0.06
     каждую
    -0.06
    POSITIVE LOGITS
     behem
    0.07
    Contents
    0.06
    뗀
    0.06
    :(
    0.06
     whimsical
    0.06
     bloodshed
    0.06
     convivial
    0.06
     thankful
    0.06
    umuz
    0.06
     zealous
    0.06
    Activations Density 0.001%

    No Known Activations