© 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. 117551
    Prev
    Next
    INDEX
    Explanations

    auto session

    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
    倒入
    -0.06
     руба
    -0.06
     révolution
    -0.06
     অনুপস্থিত
    -0.06
    ংলা
    -0.06
     optionally
    -0.05
     одним
    -0.05
    devel
    -0.05
     ലോ
    -0.05
     thanks
    -0.05
    POSITIVE LOGITS
    ProductId
    0.06
    地震
    0.06
     Grocery
    0.06
    არგ
    0.06
     Fabrizio
    0.06
    directives
    0.06
     কোভিড
    0.06
     غادي
    0.06
     महाराजा
    0.06
    議論
    0.06
    Activations Density 0.034%

    No Known Activations