© 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. 128407
    Prev
    Next
    INDEX
    Explanations

    donations of gifts and items

    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
     relics
    -0.06
     antique
    -0.06
     Mö
    -0.06
     entdecken
    -0.06
     heraus
    -0.06
     historic
    -0.06
     entdeckt
    -0.06
     obtient
    -0.06
     among
    -0.06
    遺跡
    -0.06
    POSITIVE LOGITS
     waterproofing
    0.06
     барои
    0.06
     stylists
    0.06
     desperately
    0.06
     untuk
    0.06
     According
    0.06
     हेल्पलाइन
    0.06
    陘
    0.06
     অতিরিক্ত
    0.06
     ಮಕ್ಕ
    0.05
    Activations Density 0.009%

    No Known Activations