© 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. 130480
    Prev
    Next
    INDEX
    Explanations

    Q: and A:

    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
     сег
    -0.06
     civilized
    -0.06
     структуры
    -0.06
     profilo
    -0.06
     Publik
    -0.06
    जिया
    -0.06
    二十
    -0.06
     tembok
    -0.06
    的地方
    -0.06
     twenty
    -0.06
    POSITIVE LOGITS
     variously
    0.06
    用紙
    0.06
    documents
    0.06
    document
    0.06
     having
    0.06
     თუ
    0.06
    hadoop
    0.05
    📄
    0.05
     documents
    0.05
    Document
    0.05
    Activations Density 0.004%

    No Known Activations