© 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. 120232
    Prev
    Next
    INDEX
    Explanations

    hot tubs and saunas

    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
    shap
    -0.06
     refill
    -0.06
     শাস্ত্র
    -0.06
     hounds
    -0.06
    徘
    -0.06
    注射
    -0.05
    bey
    -0.05
    notFound
    -0.05
    〽
    -0.05
     aider
    -0.05
    POSITIVE LOGITS
     내부
    0.07
    卖
    0.07
     respetar
    0.07
    廪
    0.06
    烨
    0.06
     craftsmanship
    0.06
    不同的
    0.06
     판매
    0.06
     বিবে
    0.06
     JUNE
    0.06
    Activations Density 0.045%

    No Known Activations