© 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. 116658
    Prev
    Next
    INDEX
    Explanations

    various community interactions

    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
    raphic
    -0.07
     दस्तावे
    -0.06
     photographic
    -0.06
     TRUE
    -0.06
    照片
    -0.06
    ibrant
    -0.06
     juridique
    -0.06
     práv
    -0.06
     myriad
    -0.06
     orden
    -0.06
    POSITIVE LOGITS
     अहिले
    0.06
     currently
    0.06
     ইতিমধ্যে
    0.06
     ترکیب
    0.06
     cualquier
    0.06
     qualche
    0.06
     தற்போது
    0.06
     for
    0.06
    だけど
    0.06
     когда
    0.06
    Activations Density 0.028%

    No Known Activations