© 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. 129214
    Prev
    Next
    INDEX
    Explanations

    salutationsOKBuyersThePleaseRedIStillAvantPleaseTE

    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
     einzelne
    -0.06
     при
    -0.06
     przy
    -0.06
     Ac
    -0.06
    我们在
    -0.06
     agri
    -0.06
    我們
    -0.06
    コール
    -0.05
     einzelnen
    -0.05
     But
    -0.05
    POSITIVE LOGITS
     ওই
    0.06
    这个
    0.06
     আসতে
    0.06
     possibly
    0.06
    この
    0.06
     this
    0.06
    这也是
    0.06
    univers
    0.06
    possibly
    0.06
     लागि
    0.06
    Activations Density 0.010%

    No Known Activations