© 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. 120063
    Prev
    Next
    INDEX
    Explanations

    URLs after "at"

    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
     あなた
    -0.07
     one
    -0.07
     your
    -0.07
    あなたが
    -0.06
     a
    -0.06
     specialized
    -0.06
     you
    -0.06
     tailor
    -0.06
    rystalline
    -0.06
     what
    -0.05
    POSITIVE LOGITS
    કિસ્
    0.07
     ወይም
    0.07
    尤其是
    0.07
     khususnya
    0.07
     особенно
    0.07
     특히
    0.07
     terutama
    0.07
     особливо
    0.06
     zabezpie
    0.06
     Sections
    0.06
    Activations Density 0.001%

    No Known Activations