© 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. 118421
    Prev
    Next
    INDEX
    Explanations

    TURN server, entities, Ginger Baker, mirrors, .NET, address, were changes

    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
    oline
    -0.06
    വിന്
    -0.06
    )..
    -0.06
    antine
    -0.06
    ตอนนี้
    -0.06
    file
    -0.06
    〔
    -0.06
    জেন
    -0.06
    セミナー
    -0.06
    现在
    -0.06
    POSITIVE LOGITS
     मस्ती
    0.07
     innate
    0.06
     wikipedia
    0.06
    🔽
    0.06
     chosen
    0.06
     Matrix
    0.06
     treasury
    0.06
     wersji
    0.06
    对自己
    0.06
    Amit
    0.06
    Activations Density 0.003%

    No Known Activations