© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118138
    Prev
    Next
    INDEX
    Explanations

    assistance

    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
     allerede
    -0.06
    家族
    -0.06
     уже
    -0.06
     zaten
    -0.06
     veřej
    -0.06
     porod
    -0.06
     familie
    -0.06
    既に
    -0.06
     distiller
    -0.06
    遺
    -0.06
    POSITIVE LOGITS
     weekly
    0.07
     সাপ্তাহিক
    0.06
     이곳
    0.06
     겸
    0.06
    গেট
    0.06
    ҳои
    0.06
    同时
    0.06
    真心
    0.06
     deze
    0.06
     bodily
    0.06
    Activations Density 0.009%

    No Known Activations