© 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. 117077
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by specific words

    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
     forgetting
    -0.07
     devient
    -0.07
     pierde
    -0.06
     ек
    -0.06
    MongoDB
    -0.06
     পুনরুদ্ধার
    -0.06
    比如
    -0.06
    假設
    -0.06
     overdue
    -0.06
    omości
    -0.06
    POSITIVE LOGITS
     vastly
    0.07
    only
    0.06
    mostly
    0.06
     উভয়ের
    0.06
     आवेदन
    0.06
     https
    0.06
     formal
    0.06
     SVP
    0.06
    https
    0.06
     потому
    0.06
    Activations Density 0.001%

    No Known Activations