© 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. 120332
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

    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
     or
    -0.07
     விழா
    -0.06
    /
    -0.06
    の
    -0.05
     एवं
    -0.05
     खतरा
    -0.05
     或者
    -0.05
    依旧
    -0.05
    '
    -0.05
    ni
    -0.05
    POSITIVE LOGITS
     sowohl
    0.09
     zarówno
    0.08
    不僅
    0.07
     lors
    0.07
     ৯
    0.07
     inexpensive
    0.07
    用於
    0.07
     both
    0.07
     adventurers
    0.07
     zowel
    0.06
    Activations Density 0.009%

    No Known Activations