© 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. 117719
    Prev
    Next
    INDEX
    Explanations

    scientific, technical, and musical contexts

    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
    नाने
    -0.07
     larger
    -0.06
    包装
    -0.06
     macros
    -0.06
     ভাইরাস
    -0.06
     progesterone
    -0.06
    ineties
    -0.06
     sensibly
    -0.06
    ハウス
    -0.06
    वाड
    -0.06
    POSITIVE LOGITS
     Einzel
    0.07
     lost
    0.06
    individual
    0.06
     иска
    0.06
     потеря
    0.06
     activités
    0.06
    道を
    0.06
     পথের
    0.06
    Individual
    0.06
     Individual
    0.06
    Activations Density 0.001%

    No Known Activations