© 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. 129318
    Prev
    Next
    INDEX
    Explanations

    using System;

    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
     mówi
    -0.06
     using
    -0.06
     senseless
    -0.06
     огром
    -0.06
     nachdem
    -0.06
     revisar
    -0.06
    可以用
    -0.06
    already
    -0.06
     använda
    -0.06
    ثل
    -0.05
    POSITIVE LOGITS
     of
    0.07
     TO
    0.06
     другому
    0.06
     reprezent
    0.06
     Sometimes
    0.06
    当然
    0.06
     weitere
    0.06
     कितने
    0.06
     ಮಾರ
    0.06
    डू
    0.06
    Activations Density 0.001%

    No Known Activations