© 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. 119369
    Prev
    Next
    INDEX
    Explanations

    license text

    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
    Gray
    -0.06
     grief
    -0.06
    Tony
    -0.06
     oficialmente
    -0.06
     Wh
    -0.06
     غ
    -0.06
     traditional
    -0.05
     really
    -0.05
    Jf
    -0.05
    Wh
    -0.05
    POSITIVE LOGITS
     영상을
    0.07
     may
    0.06
     некоторых
    0.06
     niektó
    0.06
     sommige
    0.06
     analyzed
    0.06
    eseorang
    0.06
     devices
    0.06
     영상
    0.06
     কেবল
    0.06
    Activations Density 0.002%

    No Known Activations